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. 25-GEMMASCOPE-RES-16K
    6. 4394
    Prev
    Next
    INDEX
    Explanations

    various programming constructs such as function definitions, method calls, and control flow statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ゴリー
    -0.49
    gree
    -0.46
    Filmografie
    -0.45
    avannah
    -0.45
    æld
    -0.45
    úrese
    -0.44
    ütfen
    -0.44
    riction
    -0.43
     !}
    -0.42
    criminator
    -0.42
    POSITIVE LOGITS
     return
    0.76
    return
    0.73
    ↵
    0.72
     pass
    0.71
    pass
    0.71
     continue
    0.62
     raise
    0.62
     الحره
    0.59
     propOrder
    0.58
    __":
    0.58
    Activations Density 0.042%

    No Known Activations