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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 9744
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and formatting elements used in equations

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

    LaTeX math environments and code

    np_acts-logits-general · gemini-2.0-flash

    HTML/LaTeX formatting tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addCriterion
    -0.52
    parsedMessage
    -0.41
     \"
    -0.37
    RegistryLite
    -0.37
     femininos
    -0.36
    uetas
    -0.36
     oração
    -0.36
     pensamentos
    -0.36
    LookAnd
    -0.35
     alça
    -0.35
    POSITIVE LOGITS
    <sup>
    0.98
    <sub>
    0.82
    <i>
    0.78
    <em>
    0.77
    <code>
    0.74
    <s>
    0.63
    </s>
    0.59
    <u>
    0.56
    }],
    0.52
    </sup>
    0.52
    Activations Density 2.884%

    No Known Activations