© 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. 116110
    Prev
    Next
    INDEX
    Explanations

    references to personnel roles and responsibilities in various contexts

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

    contexts or situations

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

    mentions of people or other agents (personal nouns and pronouns).

    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
     Exacts
    -0.59
     disponibilités
    -0.58
     الحره
    -0.57
    ➟
    -0.46
     TestBed
    -0.45
    retum
    -0.44
     betweenstory
    -0.44
     jagung
    -0.43
     sleeve
    -0.43
    
    -0.42
    POSITIVE LOGITS
    UnknownFieldSet
    0.41
    BASEPATH
    0.38
    Viited
    0.37
    Suara
    0.35
    Abit
    0.33
    ViewById
    0.33
    請繼續往下閱讀
    0.33
    more
    0.32
    niczy
    0.32
    Brainz
    0.31
    Activations Density 0.788%

    No Known Activations