© 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. 18-GEMMASCOPE-RES-16K
    11. 16118
    Prev
    Next
    INDEX
    Explanations

    proper nouns and references to people, especially in the context of their professional identities and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Precedes a verb indicating origin/affiliation

    np_acts-logits-general · gemini-2.0-flash

    person's name and their status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.74
     '.';
    -0.73
     ARXIV
    -0.68
    Datuak
    -0.67
     ModelExpression
    -0.65
    beiros
    -0.65
    InputBorder
    -0.65
    الحياه
    -0.64
    =?";
    -0.64
    MigrationBuilder
    -0.64
    POSITIVE LOGITS
     graduated
    0.91
     joined
    0.89
     hails
    0.79
     specializes
    0.79
     grew
    0.77
     joins
    0.75
     lives
    0.72
     specialises
    0.68
     specialize
    0.68
     Born
    0.66
    Activations Density 0.228%

    No Known Activations