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. 16-GEMMASCOPE-RES-16K
    6. 1638
    Prev
    Next
    INDEX
    Explanations

    references to customer service interactions or requests for assistance

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

    Category: [Year] establishments in [Location]

    np_acts-logits-general · gemini-2.0-flash

    categories in listings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tail
    -0.50
    ResumeLayout
    -0.47
    reh
    -0.46
    rep
    -0.45
     posta
    -0.45
     sync
    -0.44
     Tail
    -0.44
    æld
    -0.44
     current
    -0.44
     bosques
    -0.43
    POSITIVE LOGITS
    IsMutable
    0.77
     GenerationType
    0.76
     >=",
    0.74
    ThroughAttribute
    0.73
     propOrder
    0.61
    LayoutPanel
    0.60
    esModule
    0.60
    ſelf
    0.60
    ]")]
    0.60
     correctes
    0.58
    Activations Density 0.194%

    No Known Activations