© 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. 24248
    Prev
    Next
    INDEX
    Explanations

    references to the name "Sar" or any variations of that name in different contexts

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

    words starting with Sar

    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
     Heiligen
    -0.35
     Tempel
    -0.35
    ungsbedingungen
    -0.35
     Whitehead
    -0.33
     Kapelle
    -0.32
    REFERENCE
    -0.31
     обраща
    -0.31
    aggregate
    -0.30
    onaceous
    -0.30
    a
    -0.30
    POSITIVE LOGITS
     Sar
    0.78
    Sar
    0.76
     Sarac
    0.74
    AnchorStyles
    0.70
    rungsseite
    0.69
     sar
    0.69
     الرياضيه
    0.69
     يتيمه
    0.65
     ProtoMessage
    0.65
    windowFixed
    0.61
    Activations Density 0.018%

    No Known Activations