© 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. 31-GEMMASCOPE-RES-16K
    11. 15256
    Prev
    Next
    INDEX
    Explanations

    mention of the word "hat" and its variations and contexts

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

    the word "hat" across different contexts (scientific notation, names, and idiomatic expressions).

    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
    webElementXpaths
    -0.34
     Schiller
    -0.34
     autorytatywna
    -0.34
     Públicas
    -0.33
     yazılı
    -0.33
    SC
    -0.33
    reiche
    -0.33
    ு
    -0.33
    fromnode
    -0.33
    Pozri
    -0.32
    POSITIVE LOGITS
    Hat
    0.86
     Hat
    0.85
     hat
    0.79
    hat
    0.77
     HAT
    0.74
    HAT
    0.70
    Hatch
    0.68
     hats
    0.68
    hatch
    0.67
     Hats
    0.65
    Activations Density 0.210%

    No Known Activations