© 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. 126361
    Prev
    Next
    INDEX
    Explanations

    names and titles of various professionals and artists in the creative and academic fields

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

    profession or entity followed by name

    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
     Exacts
    -0.53
     calendriers
    -0.39
    AnchorStyles
    -0.36
     AssemblyCulture
    -0.36
     собой
    -0.36
     Himself
    -0.35
     itself
    -0.35
     Itself
    -0.35
     MainAxisSize
    -0.32
    TargetException
    -0.32
    POSITIVE LOGITS
    uxxxx
    0.51
     ligiloj
    0.47
    ArrowToggle
    0.46
    PagerAdapter
    0.45
    British
    0.45
    ViewImports
    0.45
     yyr
    0.45
    fjspx
    0.44
     stringBuilder
    0.44
    Etimología
    0.44
    Activations Density 0.040%

    No Known Activations