© 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
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 2203
    Prev
    Next
    INDEX
    Explanations

    types related to numerical data structures and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     secado
    -0.50
     Züge
    -0.49
     ventilación
    -0.49
     Vordergrund
    -0.47
    :✨
    -0.47
     nạ
    -0.45
     desaparición
    -0.45
     hvert
    -0.45
     Gefäng
    -0.45
    Voltaje
    -0.45
    POSITIVE LOGITS
    float
    0.83
     float
    0.81
    toFloat
    0.74
    parseDouble
    0.73
    FloatField
    0.72
     Float
    0.71
    parseFloat
    0.70
     parseFloat
    0.69
    Float
    0.69
    getFloat
    0.68
    Activations Density 0.385%

    No Known Activations