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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 6187
    Prev
    Next
    INDEX
    Explanations

    names of characters in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.21
    UnsafeEnabled
    -0.83
    Datuak
    -0.81
    jooq
    -0.78
    KURZBESCHREIBUNG
    -0.75
    Personendaten
    -0.73
     tartalomajánló
    -0.72
     rendus
    -0.69
    migrationBuilder
    -0.68
    ScopeManager
    -0.68
    POSITIVE LOGITS
     Pete
    0.68
     Bob
    0.65
    Bob
    0.62
    Pete
    0.62
     Joe
    0.61
     Charlie
    0.60
     Bill
    0.59
    Joe
    0.59
     Phil
    0.56
    Bill
    0.56
    Activations Density 0.326%

    No Known Activations