© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10550
    Prev
    Next
    INDEX
    Explanations

    references to machine learning model training and testing parameters

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

    Code snippets with "idx" or numbers

    np_acts-logits-general · gemini-2.0-flash

    colon separator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.60
    -------------</
    -0.59
     *)__
    -0.58
     ExecuteAsync
    -0.57
     $_(
    -0.57
    ɵɵelementStart
    -0.56
     queſta
    -0.56
     ſind
    -0.56
     <=",
    -0.55
    fillType
    -0.54
    POSITIVE LOGITS
    :
    0.59
     pegatinas
    0.48
     mío
    0.43
     bebida
    0.42
     eğiti
    0.41
     vectorielle
    0.40
     cápsulas
    0.40
     tartış
    0.39
     desmotivaciones
    0.39
     espuma
    0.39
    Activations Density 0.612%

    No Known Activations