© 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. 101742
    Prev
    Next
    INDEX
    Explanations

    syntactic structures and their relationships within the text

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

    number of items in a group

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

    sentence-structuring function words and punctuation that link clauses or mark list-like structure.

    oai_token-act-pair · gpt-5Triggered 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
     giyim
    -0.35
     defStyleAttr
    -0.35
     Komponist
    -0.34
    marle
    -0.34
    AndView
    -0.34
    fml
    -0.34
     Glä
    -0.33
     elbise
    -0.33
    sidenav
    -0.33
     Beobachtungen
    -0.33
    POSITIVE LOGITS
    ConstraintMaker
    0.56
    AndEndTag
    0.55
     HasFactory
    0.55
     AssemblyTitle
    0.53
    Бахар
    0.52
    ///</
    0.50
    __*/
    0.49
     faſt
    0.49
    /**
    0.49
     invokingState
    0.49
    Activations Density 0.072%

    No Known Activations