Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 130917
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

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

    Mathematical expression components in algebra equations, particularly variable terms and operators that define relationships in solve-for-variable problems.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    เดียว
    -0.38
    ̈́
    -0.33
     naciones
    -0.33
     /**
    
    -0.31
     officielle
    -0.31
     quisiera
    -0.31
    råd
    -0.30
     Sicherheits
    -0.30
     réussir
    -0.30
     mecánica
    -0.30
    POSITIVE LOGITS
    thus
    0.57
     الرياضيه
    0.56
    WebElementEntity
    0.54
     thereby
    0.52
    therefore
    0.50
     gesta
    0.50
    必然
    0.49
    gettext
    0.47
     htmlFor
    0.47
     BorderSide
    0.47
    Activations Density 0.294%

    No Known Activations