© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104745
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in social or legal contexts

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

    A period at the end of a complete sentence or paragraph, often marking a transition to a new topic or speaker in the text.

    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
    rungsseite
    -0.60
    TagMode
    -0.54
     ***!
    -0.46
    期刊论文
    -0.45
    Życiorys
    -0.45
    Життєпис
    -0.43
    utilisons
    -0.41
     Wiktionnaire
    -0.41
     للمعارف
    -0.40
    Біографія
    -0.40
    POSITIVE LOGITS
     مواليد
    0.58
     незавершена
    0.45
     }{@
    0.42
    cambrian
    0.41
     pous
    0.41
     Walkover
    0.38
    telse
    0.38
    stone
    0.38
    龇
    0.37
    sizeCache
    0.37
    Activations Density 0.168%

    No Known Activations