© 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. 40-GEMMASCOPE-RES-16K
    11. 7219
    Prev
    Next
    INDEX
    Explanations

    references to self and related programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.97
    RTGC
    -0.83
    RTEX
    -0.81
     Италијани
    -0.81
     мәкал
    -0.79
    :✨
    -0.74
    +#+#
    -0.74
    httphttps
    -0.73
     OMITBAD
    -0.73
     ſte
    -0.71
    POSITIVE LOGITS
    ->
    0.45
    <unused62>
    0.43
    <unused63>
    0.43
    <unused61>
    0.41
    </em>
    0.38
    </i>
    0.35
    <unused60>
    0.29
    >=
    0.27
    ,"
    0.26
    ["
    0.26
    Activations Density 0.117%

    No Known Activations