© 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. 7-GEMMASCOPE-RES-16K
    11. 15759
    Prev
    Next
    INDEX
    Explanations

    hyphenated or segmented elements, often related to identifiers or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boer
    -0.38
    mode
    -0.36
    last
    -0.35
    moj
    -0.35
    iner
    -0.34
     прико
    -0.34
    setTarget
    -0.34
    leroi
    -0.34
    dist
    -0.33
     hatchback
    -0.33
    POSITIVE LOGITS
    ScopeManager
    0.91
     MainAxisSize
    0.81
    tagHelperRunner
    0.81
    InjectAttribute
    0.69
    enumii
    0.67
    AnimationsModule
    0.65
    URLException
    0.64
     صوتيه
    0.64
    parsedMessage
    0.63
    httphttps
    0.62
    Activations Density 0.453%

    No Known Activations