© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3452
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands related to figures, graphics, or formatting

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

    LaTeX markup and formatting syntax elements.

    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
    parsedMessage
    -0.61
    setViewName
    -0.38
    دانشنامهٔ
    -0.37
    ंदीखरीदारी
    -0.35
    geslacht
    -0.35
    EndProject
    -0.35
     становника
    -0.34
     bazie
    -0.33
     ModelExpression
    -0.33
     recordings
    -0.33
    POSITIVE LOGITS
     scale
    0.72
     scaling
    0.63
     Scale
    0.62
    scale
    0.56
     Scaling
    0.55
     height
    0.52
     scaled
    0.52
     width
    0.51
    IGENCE
    0.50
    Scale
    0.49
    Activations Density 0.329%

    No Known Activations