© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8788
    Prev
    Next
    INDEX
    Explanations

    function and variable definitions in programming code

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

    Code, names, and technical terms

    np_acts-logits-general · gemini-2.0-flash

    code or phrase terminators

    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
    `,
    -1.19
    '],
    -1.18
    ],
    -1.15
    '},
    -1.11
    "],
    -1.05
    ",
    -1.05
    >",
    -1.04
    '}>
    -1.04
    ',
    -1.02
    ).</
    -1.01
    POSITIVE LOGITS
    ↵
    1.55
    ↵↵
    1.19
    ↵↵↵
    1.15
    ↵↵↵↵
    0.81
    ↵↵↵↵↵
    0.76
    .
    0.69
    <eos>
    0.66
    ↵↵↵↵↵↵
    0.64
    ()
    0.62
    ↵↵↵↵↵↵↵
    0.61
    Activations Density 0.636%

    No Known Activations