© 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. 104950
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    End-of-section markers in technical documentation and code examples, often appearing before transitions to new content.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
     EconPapers
    -1.30
    uxxxx
    -1.07
    OGND
    -1.05
     zwiſchen
    -1.04
    ſicht
    -1.02
    webElementXpaths
    -1.01
    ſehen
    -1.01
    <unused41>
    -1.00
    [@BOS@]
    -1.00
    <unused3>
    -0.99
    POSITIVE LOGITS
    The
    0.58
    With
    0.48
    This
    0.47
    In
    0.46
    I
    0.45
    No
    0.44
    Many
    0.44
    A
    0.44
    It
    0.43
    At
    0.43
    Activations Density 0.112%

    No Known Activations