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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 42826
    Prev
    Next
    INDEX
    Explanations

    lines of code or syntax elements in programming languages

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

    end of statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.96
    帖最后由
    -0.75
    Vidite
    -0.68
    yntaxException
    -0.67
     HasFactory
    -0.66
    rungsseite
    -0.65
     ***!
    -0.65
    featureID
    -0.64
    ſicht
    -0.64
    \{\\
    -0.62
    POSITIVE LOGITS
     won
    0.34
    bre
    0.32
     De
    0.30
     olmak
    0.30
     №
    0.30
     وخ
    0.29
     ieder
    0.29
     hẳn
    0.29
    layoutParams
    0.29
    <eos>
    0.29
    Activations Density 0.034%

    No Known Activations