© 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. 23811
    Prev
    Next
    INDEX
    Explanations

    references to characters or specific mentions, particularly the name "Sherlock."

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

    evaluated by

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

    words referring to people or agents (proper names and first‑person "I").

    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
    clusive
    -0.52
     مشين
    -0.52
    httphttps
    -0.50
     Peninsula
    -0.49
    efel
    -0.47
    bootstrapcdn
    -0.47
    Beskrivning
    -0.45
    orle
    -0.45
    hasMoreElements
    -0.44
    rds
    -0.44
    POSITIVE LOGITS
     HasFactory
    0.43
    ViewImports
    0.39
    typeorm
    0.38
    NameInMap
    0.36
     BeautifulSoup
    0.36
    IntoConstraints
    0.35
     Knochen
    0.34
     argint
    0.34
     CanadaChoose
    0.34
    SharedCtor
    0.34
    Activations Density 0.000%

    No Known Activations