Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2721
    Prev
    Next
    INDEX
    Explanations

    clauses that express uncertainty or ambiguity about a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.67
    migrationBuilder
    -0.56
     mergeFrom
    -0.50
    Бахар
    -0.44
    SourceChecksum
    -0.44
    EndGlobalSection
    -0.42
    TRAILING
    -0.41
     newly
    -0.39
    principalColumn
    -0.39
     AssemblyCulture
    -0.38
    POSITIVE LOGITS
     dışında
    0.85
     Alone
    0.75
     eneste
    0.74
     únicas
    0.74
     únicos
    0.73
    以外
    0.73
    only
    0.71
     seuls
    0.71
     seules
    0.70
    以外は
    0.70
    Activations Density 0.193%

    No Known Activations