© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 65658
    Prev
    Next
    INDEX
    Explanations

    numerical patterns and formats, particularly in relation to IP addresses and URLs

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

    ip addresses

    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
    AISSEE
    -0.69
    parsedMessage
    -0.69
    setCharacter
    -0.66
     ویکی‌آمباردا
    -0.64
    NUMX
    -0.63
    findpost
    -0.63
     témoig
    -0.60
    𐑥
    -0.60
    brtc
    -0.60
     AutoMapper
    -0.60
    POSITIVE LOGITS
     markt
    0.34
    sedia
    0.32
    1
    0.31
     Konf
    0.31
     palvel
    0.30
    Servico
    0.30
    Conteúdo
    0.29
     haremos
    0.29
     wystaw
    0.29
     gjø
    0.29
    Activations Density 0.020%

    No Known Activations