© 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. 7-GEMMASCOPE-RES-16K
    11. 14097
    Prev
    Next
    INDEX
    Explanations

    various forms of dashed or underlined separators within text

    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
    pushFollow
    -0.50
    saraba
    -0.44
    ksikon
    -0.40
    Skocz
    -0.39
    entraînement
    -0.37
    <?,
    -0.36
    ⎧
    -0.36
     voet
    -0.35
    stdio
    -0.35
    しゃれ
    -0.35
    POSITIVE LOGITS
    tagHelperRunner
    0.62
     Administrativna
    0.51
     endfor
    0.48
    \{\\
    0.48
     -}
    0.47
    󠁿
    0.46
    ptonshire
    0.46
     noDo
    0.45
     +
    0.45
     '))
    0.44
    Activations Density 0.593%

    No Known Activations