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. 8106
    Prev
    Next
    INDEX
    Explanations

    mentions of software and its related aspects

    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
     newOwner
    -0.63
    ividual
    -0.61
     mergeFrom
    -0.61
    ^(@)
    -0.61
    intios
    -0.58
     useAppContext
    -0.56
     Taktlose
    -0.53
    "):
    
    -0.52
    ThroughAttribute
    -0.52
    stateMutability
    -0.51
    POSITIVE LOGITS
    ware
    0.72
    ecore
    0.61
    Autoritní
    0.61
    IntoConstraints
    0.61
     henne
    0.61
    ße
    0.61
     lccn
    0.60
     StatefulWidget
    0.60
    \]
    0.59
    гл
    0.58
    Activations Density 0.434%

    No Known Activations