© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11384
    Prev
    Next
    INDEX
    Explanations

    words related to particular specifications or details in technical contexts

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

    words with specific syllable patterns, particularly focusing on multi-syllable technical terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    word fragments that appear at the beginning or middle of longer words, particularly syllables that start with consonant clusters or uncommon letter combinations.

    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
    shame
    -0.58
     kohta
    -0.54
     nostalgia
    -0.48
     Lolita
    -0.48
     mesmerizing
    -0.47
    bandicam
    -0.47
     deepening
    -0.47
    sibly
    -0.46
    tshell
    -0.46
    myth
    -0.46
    POSITIVE LOGITS
    ніципалі
    0.48
    HasBeenSet
    0.43
    новништво
    0.42
    pushFollow
    0.39
    onPressed
    0.39
     ſche
    0.38
    tagext
    0.37
    ("")]
    0.36
    =()=>{
    0.36
     "<?
    0.36
    Activations Density 0.394%

    No Known Activations