© 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. 105210
    Prev
    Next
    INDEX
    Explanations

    contractions and possessive pronouns

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

    Apostrophes in possessive constructions and negative contractions, along with punctuation marks that appear before or after direct speech.

    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
    StructEnd
    -0.60
     typelib
    -0.57
    parsedMessage
    -0.54
    ंदीखरीदारी
    -0.53
    DockStyle
    -0.51
     OMITBAD
    -0.49
    पया
    -0.47
     mergeFrom
    -0.46
    EClass
    -0.46
    MessageOf
    -0.45
    POSITIVE LOGITS
    WebElementEntity
    0.52
    RegressionTest
    0.42
    PostInfinity
    0.41
    Chapter
    0.38
     Chapter
    0.37
     chapter
    0.36
    Exhibition
    0.36
    Observ
    0.36
     intptr
    0.35
     Ronde
    0.35
    Activations Density 0.007%

    No Known Activations