© 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. 40-GEMMASCOPE-RES-16K
    11. 6004
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.39
    webElementXpaths
    -0.38
     Paglinawan
    -0.38
    Bibliograf
    -0.37
    irical
    -0.37
    vignon
    -0.36
    INCT
    -0.36
     Handwerk
    -0.35
    olia
    -0.35
    órc
    -0.35
    POSITIVE LOGITS
     score
    0.96
     Score
    0.85
    score
    0.84
     gameOver
    0.81
    Score
    0.81
    GameOver
    0.75
     scoreboard
    0.73
     GAME
    0.72
     scoring
    0.72
     game
    0.71
    Activations Density 0.129%

    No Known Activations