© 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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2940
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs that describe qualities or states

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

    the conjunction "and" connecting two adjectives or descriptive phrases.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     рода
    -0.40
    adaptiveStyles
    -0.40
    ญิง
    -0.38
     suivantes
    -0.38
    更好的
    -0.36
    VersionUID
    -0.36
    CAPTION
    -0.36
    uxxxx
    -0.36
     quelcon
    -0.36
    馭
    -0.36
    POSITIVE LOGITS
    featureID
    0.58
     informative
    0.57
     effective
    0.57
     nuanced
    0.56
     productive
    0.56
     resourceful
    0.55
     impactful
    0.55
     efficient
    0.54
     persuasive
    0.53
     flexible
    0.53
    Activations Density 0.302%

    No Known Activations