© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4444
    Prev
    Next
    INDEX
    Explanations

    sections that express opinion or analysis on various topics

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

    narrative statements that reveal surprising or consequential information.

    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
    various
    -0.57
     various
    -0.56
    ต่างๆ
    -0.56
     Various
    -0.56
    Various
    -0.54
     variously
    -0.50
     berbagai
    -0.49
    Either
    -0.49
     Either
    -0.47
    各種
    -0.47
    POSITIVE LOGITS
     something
    1.30
    Something
    1.05
    something
    1.05
     Something
    0.98
     another
    0.94
     etwas
    0.82
     iets
    0.77
     SOMETHING
    0.77
     somethin
    0.75
    还有一个
    0.75
    Activations Density 0.549%

    No Known Activations