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. 20-GEMMASCOPE-RES-16K
    6. 1483
    Prev
    Next
    INDEX
    Explanations

    words related to specific actions or conditions that require attention or caution

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

    Code, abbreviations, and symbols

    np_acts-logits-general · gemini-2.0-flash

    BCA interview t

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h1>
    -0.66
     الدولى
    -0.65
     …
    -0.62
    </strong>
    -0.55
    ↵↵
    -0.55
    setVerticalGroup
    -0.51
    fsch
    -0.49
    ↵↵↵
    -0.47
    fortawesome
    -0.46
    …
    -0.46
    POSITIVE LOGITS
    ArgsConstructor
    1.02
     NDEBUG
    0.94
    ViewImports
    0.92
    Personendaten
    0.86
     myſelf
    0.84
    〢
    0.82
     $_"
    0.81
    `;
    
    0.80
     समीक्षक
    0.78
    EndContext
    0.77
    Activations Density 5.828%

    No Known Activations