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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14569
    Prev
    Next
    INDEX
    Explanations

    themes related to music and songs

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

    punctuation and numbering markers in names/titles (especially apostrophes, hyphenated separators, initials/ampersands/parentheses, and year or version digits), as seen in tracklists and filmographies.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     AssemblyCulture
    -0.68
     оригіналу
    -0.61
    writeFieldEnd
    -0.57
     يتيمه
    -0.56
    ↹
    -0.54
    bootstrapcdn
    -0.53
     مشين
    -0.53
    fromnode
    -0.51
    parsedMessage
    -0.49
    StructEnd
    -0.48
    POSITIVE LOGITS
    <eos>
    0.47
    Vers
    0.45
     checklists
    0.45
    Scri
    0.44
    ▒
    0.43
    uidado
    0.43
    Still
    0.41
     Vers
    0.41
    Hé
    0.41
    Exist
    0.40
    Activations Density 0.219%

    No Known Activations