© 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. 38-GEMMASCOPE-RES-16K
    11. 14740
    Prev
    Next
    INDEX
    Explanations

    code structure and programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gallery
    -0.27
     compiler
    -0.24
     programming
    -0.24
    一来
    -0.24
     tag
    -0.24
     Tabor
    -0.23
    ら
    -0.23
    GALLERY
    -0.23
     BMW
    -0.23
     housing
    -0.23
    POSITIVE LOGITS
    gdx
    0.96
     nahilalakip
    0.95
    Gdx
    0.88
    httphttps
    0.81
    ScopeManager
    0.79
     autorytatywna
    0.79
    abestanden
    0.74
     AssemblyCulture
    0.73
    badlogic
    0.72
    expandindo
    0.70
    Activations Density 0.181%

    No Known Activations