© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 38312
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of shepherding or stewardship, particularly in a metaphorical or spiritual context

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

    shepherd and herding

    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
    i
    -0.35
    ا
    -0.34
    a
    -0.32
    s
    -0.32
    is
    -0.30
    ItemType
    -0.30
    boutin
    -0.28
     Late
    -0.28
    o
    -0.28
    u
    -0.28
    POSITIVE LOGITS
    Shepherd
    1.06
     Shepherd
    1.03
     shepherd
    0.85
     Shepherds
    0.83
    pherds
    0.79
    pherd
    0.78
     shepherds
    0.70
    ロウィン
    0.70
    ipheral
    0.68
    IVEREF
    0.67
    Activations Density 0.003%

    No Known Activations