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. 11-GEMMASCOPE-RES-16K
    6. 13240
    Prev
    Next
    INDEX
    Explanations

    names of band members and their roles in music

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    referrer
    -0.46
     Arden
    -0.42
    oxidants
    -0.40
     raso
    -0.40
    PING
    -0.40
    vernment
    -0.39
     billions
    -0.39
     ability
    -0.39
     Republic
    -0.39
    Suspense
    -0.39
    POSITIVE LOGITS
    GraphicsUnit
    0.78
    ScopeManager
    0.76
    ThroughAttribute
    0.75
    PreferredItem
    0.71
     चीज़ों
    0.70
    bootstrapcdn
    0.69
    AccessorTable
    0.68
    verifyException
    0.68
    AsUp
    0.66
     مشين
    0.66
    Activations Density 0.102%

    No Known Activations