© 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. 21130
    Prev
    Next
    INDEX
    Explanations

    numerical measurements and specifications related to physical objects

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

    diameter and radius measurements

    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
    BagConstraints
    -0.47
    MethodManager
    -0.46
     TextInputType
    -0.43
    -------------</
    -0.42
     CreateTagHelper
    -0.42
    complexContent
    -0.40
    AddTagHelper
    -0.40
    Cubit
    -0.39
    autaire
    -0.39
    ScopeManager
    -0.37
    POSITIVE LOGITS
     diameter
    1.75
     Diameter
    1.56
    diameter
    1.51
    Diameter
    1.50
     diameters
    1.48
     Durchmesser
    1.41
     radius
    1.37
    直径
    1.33
     diamètre
    1.32
     диамет
    1.24
    Activations Density 0.210%

    No Known Activations