© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 120098
    Prev
    Next
    INDEX
    Explanations

    sentences with strong punctuations such as periods and exclamation marks

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

    start of sentence

    np_acts-logits-general · gemini-2.5-flash-lite

    sentence endings or sentence-final punctuation (periods, closing quotes, etc.).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     AssemblyCulture
    -0.58
    govina
    -0.44
    évaluateur
    -0.43
     Réponses
    -0.42
     bowiem
    -0.41
    dersfield
    -0.40
    Jeografia
    -0.40
    下载附件
    -0.39
    componentDid
    -0.39
    Gambas
    -0.38
    POSITIVE LOGITS
    ActionCreators
    0.49
    KommentareTeilen
    0.48
    ISupport
    0.41
    ValueGeneration
    0.41
    DataBinding
    0.40
    skull
    0.40
    awtextra
    0.40
    .*")]
    0.39
    Personensuche
    0.39
    jmniej
    0.38
    Activations Density 0.573%

    No Known Activations