© 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. 12025
    Prev
    Next
    INDEX
    Explanations

    conditional language and terms related to optionality and support in technical contexts

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

    recommendation

    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
     الحره
    -0.42
     Pingback
    -0.38
     listo
    -0.38
     vectorielles
    -0.37
     plegable
    -0.36
     titoli
    -0.35
    messageInfo
    -0.35
     viewType
    -0.35
     tell
    -0.34
    enterOuterAlt
    -0.34
    POSITIVE LOGITS
     recommended
    1.20
     recommends
    1.17
     recommend
    1.16
     recomendamos
    1.12
    recommended
    1.10
     рекомендуется
    1.09
    Recommended
    1.06
     Recommended
    1.05
    recommend
    1.04
    建议
    1.02
    Activations Density 0.059%

    No Known Activations