© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 5398
    Prev
    Next
    INDEX
    Explanations

    technical and statistical terms related to mathematical modeling and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Avila
    -0.49
    ".
    -0.48
    <h4>
    -0.48
     zeroes
    -0.44
     Ayres
    -0.43
     Oester
    -0.42
     Vasile
    -0.42
    Emile
    -0.42
     Beattie
    -0.42
    ",
    -0.42
    POSITIVE LOGITS
    FIG
    0.65
    ,'
    0.63
     ModelExpression
    0.61
    ,”
    0.60
    ,’
    0.59
     Wikimedijinoj
    0.58
     HasFactory
    0.57
    EDEFAULT
    0.57
     noDo
    0.57
    .,"
    0.55
    Activations Density 1.028%

    No Known Activations