© 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. 103
    Prev
    Next
    INDEX
    Explanations

    statements that emphasize notable points or important observations

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

    the phrase "It should be noted" and similar formal disclaimer statements.

    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
    uxxxx
    -0.40
     виправивши
    -0.37
     ser
    -0.35
     lis
    -0.34
    綢
    -0.33
     concorso
    -0.32
     Moore
    -0.31
    setof
    -0.31
    Greet
    -0.30
     SER
    -0.30
    POSITIVE LOGITS
     note
    2.20
     Note
    1.88
    note
    1.73
    Note
    1.73
     remember
    1.59
     NOTE
    1.54
    NOTE
    1.43
     noter
    1.38
     Remember
    1.38
    Remember
    1.34
    Activations Density 0.843%

    No Known Activations