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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8878
    Prev
    Next
    INDEX
    Explanations

    copyright and licensing information

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

    Boost license information

    np_acts-logits-general · gemini-2.0-flash

    version numbers and licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ‚
    -0.76
    ...",
    -0.74
    ",
    -0.73
    !",
    -0.71
    ”,
    -0.71
    …,
    -0.68
    ?",
    -0.68
    <i>
    -0.66
    ;"><
    -0.66
    <sup>
    -0.66
    POSITIVE LOGITS
    }
    0.85
    </h3>
    0.78
    enumi
    0.73
    </h4>
    0.71
     مشين
    0.69
     الحره
    0.67
    culosis
    0.65
    .}
    0.64
    DoubleQuotes
    0.63
     }}$}
    0.62
    Activations Density 0.004%

    No Known Activations