© 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 EvalsExportsAPI 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. 9790
    Prev
    Next
    INDEX
    Explanations

    numerical values and comparisons related to events or scores

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

    Team or person losing/behind

    np_acts-logits-general · gemini-2.0-flash

    scores and deficits

    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
    )++;
    -0.69
    AccessorTable
    -0.68
     صوتيه
    -0.67
     <=",
    -0.66
    DoubleQuotes
    -0.66
    MessageOf
    -0.65
     تضيفلها
    -0.63
    compared
    -0.62
    الإنجليزية
    -0.62
     compared
    -0.62
    POSITIVE LOGITS
     by
    0.61
     AssemblyCulture
    0.55
    Coordenadas
    0.52
    ngrx
    0.47
    ApiRequest
    0.47
    migrationBuilder
    0.47
     incontra
    0.46
    ContentAlignment
    0.46
    Sprintf
    0.46
    NgModule
    0.45
    Activations Density 0.208%

    No Known Activations