© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10739
    Prev
    Next
    INDEX
    Explanations

    active verbs and phrases expressing assertive opinions or statements

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

    Attribution with verbs like "says," "said," and "suggests."

    np_acts-logits-general · gemini-2.0-flash

    verbs and possessive pronouns

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Conventional
    -0.26
     cadeiras
    -0.25
     soru
    -0.25
    ประเทศ
    -0.25
     ocurrido
    -0.25
     alternatives
    -0.25
     ocurrir
    -0.25
    ข้าว
    -0.25
     Middleton
    -0.24
    identité
    -0.24
    POSITIVE LOGITS
    himself
    0.98
     himself
    0.93
     Himself
    0.89
    tagHelperRunner
    0.88
     himſelf
    0.84
    His
    0.84
     ſeiner
    0.79
     Menſchen
    0.77
     Geiſt
    0.77
     zijne
    0.76
    Activations Density 0.485%

    No Known Activations