© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 82841
    Prev
    Next
    INDEX
    Explanations

    author attribution and affiliations in academic or research contexts

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

    names and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     surla
    -0.62
     ligiloj
    -0.61
    tanleria
    -0.57
     OMITBAD
    -0.55
    transQ
    -0.52
    twimg
    -0.52
    findpost
    -0.51
    ">//
    -0.50
    -------------</
    -0.49
     ویکی‌پدی
    -0.49
    POSITIVE LOGITS
     volunteers
    0.39
     portfolio
    0.37
     Ause
    0.37
     Volunteer
    0.37
     volunteer
    0.36
     Beam
    0.36
    volunteer
    0.36
     Resident
    0.35
    portfolio
    0.35
     Rachel
    0.34
    Activations Density 0.018%

    No Known Activations