© 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
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7242
    Prev
    Next
    INDEX
    Explanations

    references to research methodologies and ethical considerations in studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zelve
    -0.53
     gekomen
    -0.45
     gevo
    -0.41
     voorbere
    -0.37
     Tre
    -0.37
     geweldig
    -0.36
     dezelve
    -0.36
     gewel
    -0.36
     moeili
    -0.34
     zijne
    -0.34
    POSITIVE LOGITS
    
    0.68
     HasFactory
    0.66
     يتيمه
    0.66
     للاسماء
    0.64
     pinulongan
    0.63
    liceerd
    0.60
     Delft
    0.57
    endregion
    0.56
     transfieras
    0.56
    Bronnen
    0.54
    Activations Density 0.979%

    No Known Activations