© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 101233
    Prev
    Next
    INDEX
    Explanations

    elements related to skill assessments or descriptions

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

    Period or other punctuation marks that appear at the end of a section, often marking the conclusion of technical documentation, code structures, or academic proofs - frequently in contexts like bibliographic entries, software documentation, or mathematical texts.

    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
    OGND
    -0.96
    Personendaten
    -0.91
    ScopeManager
    -0.79
    verifyException
    -0.78
    ########.
    -0.77
    SourceChecksum
    -0.76
    ロウィン
    -0.73
    StoryboardSegue
    -0.73
    ſcher
    -0.72
     EconPapers
    -0.71
    POSITIVE LOGITS
    <eos>
    0.46
    ↵↵
    0.45
     Rose
    0.39
    ↵
    0.39
     Lor
    0.36
    .
    0.36
     Ros
    0.36
     Don
    0.35
     
    0.35
    0
    0.35
    Activations Density 0.052%

    No Known Activations