© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8771
    Prev
    Next
    INDEX
    Explanations

    HTML headings and structure within the document

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

    HTML closing tags, particularly `</h2>` and whitespace/formatting tokens that appear at the end of markup sections.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.59
     Infórmanos
    -0.50
    ValueStyle
    -0.49
    skjaer
    -0.49
     للاسماء
    -0.48
    EnableWeb
    -0.47
     Moraes
    -0.47
     curb
    -0.46
     ſind
    -0.46
     OBIT
    -0.46
    POSITIVE LOGITS
    </h2>
    0.72
    </h3>
    0.67
    </h6>
    0.67
    </h4>
    0.66
     Audiodateien
    0.64
    KommentareTeilen
    0.64
    </h1>
    0.63
    </h5>
    0.62
    <h3>
    0.61
    <h4>
    0.61
    Activations Density 0.022%

    No Known Activations