© 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. 0-GEMMASCOPE-RES-16K
    11. 4945
    Prev
    Next
    INDEX
    Explanations

    the word "ber" in various forms, indicating a focus on specific terms related to a name or identifier

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iconos
    -0.59
     Tron
    -0.57
    snip
    -0.48
    blad
    -0.48
    MLL
    -0.48
    ガニック
    -0.47
    באנגלית
    -0.47
    ječ
    -0.47
    dungen
    -0.47
    kull
    -0.47
    POSITIVE LOGITS
    <?
    0.79
     RISERV
    0.78
     незавершена
    0.77
     onPostExecute
    0.76
    extAlignment
    0.75
     Zhou
    0.75
    Predecesor
    0.74
    RectangleBorder
    0.73
    ViewFeatures
    0.70
    Zhou
    0.69
    Activations Density 0.087%

    No Known Activations