© 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. 7762
    Prev
    Next
    INDEX
    Explanations

    queries related to alternatives or options

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

    sentences ending with periods or question marks that conclude problem statements or requests for help.

    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
     <=",
    -0.76
    MessageOf
    -0.63
    writeField
    -0.61
    Aholisi
    -0.59
    TemporalType
    -0.58
    يكب
    -0.58
    SourceChecksum
    -0.58
    rungsseite
    -0.57
    Parcelize
    -0.56
     متعلقه
    -0.55
    POSITIVE LOGITS
     anyone
    2.05
     anybody
    1.90
     Anyone
    1.89
    Anyone
    1.88
     Anybody
    1.86
    anyone
    1.80
    Anybody
    1.73
     ANYONE
    1.45
    任何人
    1.13
     any
    1.01
    Activations Density 0.376%

    No Known Activations