Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 12772
    Prev
    Next
    INDEX
    Explanations

    names of people, specifically variations of the name 'Sheryl'

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

    names ending in 'ryl', 'ryn', 'nae'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     MainAxisSize
    -0.63
     للاسماء
    -0.57
    TargetException
    -0.54
    MessageOf
    -0.50
    utnik
    -0.49
     Audiodateien
    -0.48
    StoryboardSegue
    -0.48
     ویکی‌پدی
    -0.48
     informée
    -0.48
     OMIT
    -0.47
    POSITIVE LOGITS
    tvguidetime
    0.47
     /\.(
    0.47
    bibitem
    0.41
     nonatomic
    0.39
    OPHER
    0.39
    pă
    0.37
    yn
    0.37
    nloa
    0.36
    éviter
    0.34
    -------
    0.32
    Activations Density 0.027%

    No Known Activations