© 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. 563
    Prev
    Next
    INDEX
    Explanations

    concerns related to healthcare, taxes, and the implications of insurance on society

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

    before various forms of "generation" or similar concepts

    np_acts-logits-general · gemini-2.0-flash

    generations, lives, or benefits

    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
    ніципалі
    -0.67
     GenerationType
    -0.65
     Autorizaciones
    -0.56
    IntoConstraints
    -0.55
     HasFactory
    -0.55
     OnInit
    -0.54
    Sonja
    -0.51
     يتيمه
    -0.51
    omla
    -0.50
    intios
    -0.50
    POSITIVE LOGITS
     Abonnez
    0.34
     brothers
    0.33
     generasi
    0.31
     tekem
    0.31
     generations
    0.31
     œufs
    0.30
     sœurs
    0.30
     nationaux
    0.29
     générations
    0.29
    AutoField
    0.29
    Activations Density 0.250%

    No Known Activations