© 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-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 15160
    Prev
    Next
    INDEX
    Explanations

    recognized awards and nominations in the literary and entertainment fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*")]
    -0.92
    AndEndTag
    -0.92
    HtmlAttribute
    -0.84
    migrationBuilder
    -0.79
    SequentialGroup
    -0.79
    ViewFeatures
    -0.78
    TagMode
    -0.78
    >):
    -0.77
    >--}}
    -0.77
    ')):
    -0.77
    POSITIVE LOGITS
     supplémentaire
    0.46
     mücade
    0.41
     nominee
    0.40
     dupla
    0.40
     række
    0.40
     medarbe
    0.40
    rodní
    0.39
     seca
    0.39
     dobles
    0.39
     Lett
    0.38
    Activations Density 0.392%

    No Known Activations