© 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. 29996
    Prev
    Next
    INDEX
    Explanations

    phrases that express personal beliefs and reflections

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

    scientific notation numbers

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

    Tokens that occur at the start of a sentence or clause (i.e., sentence-initial content words).

    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
     room
    -0.39
    красивые
    -0.38
    altezza
    -0.36
     strå
    -0.35
    CompoundButton
    -0.35
     commencé
    -0.35
    SessionId
    -0.35
     viaggio
    -0.34
     kemenangan
    -0.34
     Spe
    -0.34
    POSITIVE LOGITS
    Diweddarwch
    0.54
    AndroidJUnit
    0.54
     חיצוניים
    0.50
     CallOverrides
    0.47
     FetchType
    0.46
    AISSEE
    0.45
    addContainerGap
    0.45
     Realism
    0.44
    ->___
    0.44
     iParam
    0.43
    Activations Density 0.063%

    No Known Activations