© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 116
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and object properties

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

    Fragments of words

    np_acts-logits-general · gemini-2.0-flash

    action verbs and auxiliaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    tagHelperRunner
    -0.78
     initComponents
    -0.72
    StructEnd
    -0.66
    AndEndTag
    -0.65
    parsedMessage
    -0.63
    kháu
    -0.61
     AssemblyCulture
    -0.60
    :+:
    -0.60
    __':
    -0.58
    rrggbb
    -0.58
    POSITIVE LOGITS
     does
    0.85
    Does
    0.79
    does
    0.76
     Does
    0.74
     doth
    0.63
     DOES
    0.63
    volves
    0.60
    Doesn
    0.58
    izes
    0.56
    uje
    0.54
    Activations Density 0.037%

    No Known Activations