© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13553
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressions and pauses in dialogue

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

    punctuation marks, particularly dashes and commas that separate clauses or ideas in formal written text.

    oai_token-act-pair · claude-4-5-haikuTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.47
    RenderAtEndOf
    -0.47
     rodillas
    -0.46
     invokingState
    -0.36
    actéristique
    -0.36
     casquette
    -0.35
     bolsillos
    -0.34
     válvulas
    -0.34
    enumi
    -0.33
    Rese
    -0.33
    POSITIVE LOGITS
    excuse
    0.58
     uh
    0.57
    呃
    0.57
     Excuse
    0.56
     um
    0.54
     sorry
    0.54
     yeah
    0.53
     excuse
    0.52
    Xna
    0.50
     Sorry
    0.50
    Activations Density 0.070%

    No Known Activations