© 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. 35-GEMMASCOPE-RES-16K
    11. 9541
    Prev
    Next
    INDEX
    Explanations

    HTML block elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utilisons
    -0.52
    subplots
    -0.40
    pland
    -0.37
    ilem
    -0.36
    asztok
    -0.35
     Fiche
    -0.35
    InInspector
    -0.35
     iNdEx
    -0.34
    timis
    -0.34
    Defendant
    -0.34
    POSITIVE LOGITS
    httphttps
    0.66
     betweenstory
    0.54
     disambiguazione
    0.51
     jsPsych
    0.48
     snippetHide
    0.46
     ModelExpression
    0.46
    GTCX
    0.46
    dafx
    0.42
    IntoConstraints
    0.42
     Chwiliwch
    0.42
    Activations Density 0.082%

    No Known Activations