© 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. 6084
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to graph theory and edge relationships

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

    phrases contrasting or connecting "real" with "virtual" or "and" in technical contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
    CompleteListener
    -0.45
     kaynağından
    -0.45
    twimg
    -0.45
    argout
    -0.40
    SourceChecksum
    -0.40
    حوالہ
    -0.40
     ExecuteAsync
    -0.37
    serviceWorker
    -0.36
    SequentialGroup
    -0.36
    SharedDtor
    -0.36
    POSITIVE LOGITS
     fake
    2.48
    fake
    2.16
     fictitious
    2.14
     Fake
    2.11
    Fake
    2.06
     simulated
    2.06
     faked
    1.96
     phony
    1.93
     faux
    1.93
     artificial
    1.93
    Activations Density 1.457%

    No Known Activations