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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 73715
    Prev
    Next
    INDEX
    Explanations

    references to drugs, their substances, and their effects

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

    Prepositional phrases or connector words that establish relationships between entities in technical, legal, or academic documents.

    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
     propOrder
    -0.73
    DeleteBehavior
    -0.66
     CreateTagHelper
    -0.65
    AndEndTag
    -0.60
     <<<<<<<<<<<<<<
    -0.59
    +:+
    -0.58
    zki
    -0.56
    FieldBuilder
    -0.56
    出版年
    -0.55
     estekak
    -0.54
    POSITIVE LOGITS
     jspb
    0.35
    apimachinery
    0.31
     poffible
    0.30
     tranſ
    0.29
     porcentual
    0.29
     ſta
    0.28
    TokenNameRPAREN
    0.28
     diſt
    0.28
    しかも
    0.28
    เฉ
    0.28
    Activations Density 0.265%

    No Known Activations