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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 104958
    Prev
    Next
    INDEX
    Explanations

    elements related to legal terms and proceedings

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

    Section headers or titles in structured documents that separate major content sections, often followed by separator characters or whitespace.

    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
    WebElementEntity
    -0.81
    reportWebVitals
    -0.75
    AddTagHelper
    -0.71
    :✨
    -0.70
     Biôgrafia
    -0.69
     nakalista
    -0.66
    IsContent
    -0.65
     ujednoznacz
    -0.62
    writeFieldEnd
    -0.60
     ModelExpression
    -0.60
    POSITIVE LOGITS
     lately
    0.37
     Recently
    0.35
     presently
    0.35
    Recently
    0.35
     Presently
    0.35
    privilege
    0.33
    carril
    0.33
     Connectez
    0.32
     StyleSheet
    0.32
     recently
    0.32
    Activations Density 0.040%

    No Known Activations