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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 8142
    Prev
    Next
    INDEX
    Explanations

    references to external resources or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.68
    OrBuilder
    -0.61
    }")
    
    -0.57
     nakalista
    -0.57
    WebVitals
    -0.56
    principalColumn
    -0.56
     parseFrom
    -0.55
     ControllerBase
    -0.55
    SharedCtor
    -0.54
    ]";
    -0.52
    POSITIVE LOGITS
    external
    1.21
    External
    1.18
     External
    1.12
     external
    1.11
     externally
    1.03
     EXTERNAL
    0.99
     internally
    0.96
     Extern
    0.95
    EXTERNAL
    0.92
     externes
    0.90
    Activations Density 0.143%

    No Known Activations