© 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. 31-GEMMASCOPE-RES-131K
    11. 62016
    Prev
    Next
    INDEX
    Explanations

    references to medical and scientific procedures, analysis, and methodology

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

    as well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ClientRect
    -0.44
    今度は
    -0.42
    といって
    -0.41
    errHandler
    -0.40
    ']['
    -0.40
    forName
    -0.39
    たって
    -0.39
    tomans
    -0.38
    Lähteet
    -0.38
     AttributeSet
    -0.36
    POSITIVE LOGITS
     sowie
    2.03
    以及
    1.88
     ainsi
    1.87
     plus
    1.80
     serta
    1.79
     nonché
    1.78
    sowie
    1.69
     valamint
    1.67
     oraz
    1.64
     además
    1.60
    Activations Density 0.734%

    No Known Activations