© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 489
    Prev
    Next
    INDEX
    Explanations

    references to past events and their implications

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

    a prior time or event

    np_acts-logits-general · gemini-2.0-flash

    previous and earlier events

    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
    expandindo
    -0.68
    Tikang
    -0.56
     linkovi
    -0.56
    Географиясе
    -0.50
    Географи
    -0.49
    recated
    -0.48
    ArgsConstructor
    -0.48
    bootstrapcdn
    -0.48
     Ause
    -0.47
     kaarangay
    -0.47
    POSITIVE LOGITS
     previous
    0.75
     earlier
    0.66
    previous
    0.61
     vorige
    0.60
    Previous
    0.55
     vorher
    0.55
    Earlier
    0.54
     wcześ
    0.53
     Earlier
    0.53
     anteriores
    0.52
    Activations Density 0.504%

    No Known Activations