© 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. 12525
    Prev
    Next
    INDEX
    Explanations

    specifications and details related to flow rates and measurement units in experimental contexts

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

    flow rate measurement

    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
    astéro
    -0.41
    rapnel
    -0.39
    hopal
    -0.38
     mord
    -0.37
    tagHelperRunner
    -0.37
     brie
    -0.36
    dirond
    -0.36
     тен
    -0.35
     مرئيه
    -0.35
     REP
    -0.35
    POSITIVE LOGITS
     flow
    1.19
    流量
    1.02
     Flow
    1.02
     flows
    1.00
     débit
    0.98
    flow
    0.94
     Flows
    0.91
    Flow
    0.91
     rate
    0.89
     FLOW
    0.89
    Activations Density 0.048%

    No Known Activations