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. 117391
    Prev
    Next
    INDEX
    Explanations

    specific clauses and phrases related to methods or processes in research contexts

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

    Connective elements in scientific texts that link subjects with their descriptions or join clauses containing important technical information.

    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
    <unused79>
    -0.81
    <unused28>
    -0.81
    <unused8>
    -0.81
    [@BOS@]
    -0.81
    <unused51>
    -0.81
    <unused52>
    -0.81
    <unused41>
    -0.80
    ſelf
    -0.80
    <unused14>
    -0.80
    <unused3>
    -0.80
    POSITIVE LOGITS
     Hinweis
    0.28
     célé
    0.28
    ↵
    0.27
    pu
    0.27
    Bibliographie
    0.26
    le
    0.26
    enumi
    0.26
     significados
    0.26
    item
    0.25
     Erinner
    0.25
    Activations Density 0.171%

    No Known Activations