© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 9973
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to processing and transformation in various scientific contexts

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

    state changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     telah
    -0.73
     đã
    -0.68
    웠
    -0.61
     existed
    -0.60
     weren
    -0.60
     hadn
    -0.60
     consisted
    -0.59
     않았
    -0.59
    已经
    -0.57
     lacked
    -0.57
    POSITIVE LOGITS
     becomes
    1.21
     gets
    1.09
     goes
    0.92
     takes
    0.89
     begins
    0.86
    becomes
    0.85
     receives
    0.85
     develops
    0.85
     starts
    0.84
     comes
    0.83
    Activations Density 0.791%

    No Known Activations