© 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. 9-GEMMASCOPE-RES-131K
    11. 38463
    Prev
    Next
    INDEX
    Explanations

    mathematical operations, specifically multiplication, in the context of matrices or numerical calculations

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

    multiplication and product

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.52
    Personendaten
    -0.48
    \{\\
    -0.38
     nahilalakip
    -0.38
     mergeFrom
    -0.37
    contentLoaded
    -0.37
    ագրություններ
    -0.37
    WaitGroup
    -0.34
    Personensuche
    -0.33
    GEBURTS
    -0.33
    POSITIVE LOGITS
     Multiply
    0.72
     multiplying
    0.71
    Multiply
    0.66
     multiplication
    0.65
     multiplied
    0.65
     Multiplication
    0.63
    multiply
    0.61
    Multiplication
    0.57
     multiplier
    0.57
    multiplication
    0.56
    Activations Density 0.622%

    No Known Activations