© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2002
    Prev
    Next
    INDEX
    Explanations

    information related to security keys and their association in technology contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words that appear in pairs or sequences that complete a phrase or concept (like "private key", "matching X", "to go").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    words in contexts discussing matching, coordinating, or pairing items together (like clothing accessories, food and wine, or cryptographic key pairs).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to paired or coordinated items—things that match, go together, or form a pair.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueGeneration
    -0.54
    évaluateur
    -0.50
    Parcelize
    -0.48
     surla
    -0.45
     ProtoMessage
    -0.44
    bitField
    -0.43
    enderror
    -0.42
    ckley
    -0.42
     /\.
    -0.40
     Lightboxes
    -0.38
    POSITIVE LOGITS
     matching
    2.56
     matched
    2.25
    matching
    2.19
     Matching
    2.19
     match
    2.11
    Matching
    2.11
     matches
    1.91
     MATCH
    1.91
    match
    1.82
    matched
    1.80
    Activations Density 0.392%

    No Known Activations