© 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. 39-GEMMASCOPE-RES-16K
    6. 2656
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computing and data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cshtml
    -0.60
     wordpress
    -0.56
     selfies
    -0.52
     Pinterest
    -0.51
     pinterest
    -0.49
     instagram
    -0.49
     ️
    -0.49
     Instagram
    -0.49
     blogger
    -0.48
     tumblr
    -0.47
    POSITIVE LOGITS
     UNIX
    0.58
     daß
    0.56
     disk
    0.54
    UNIX
    0.53
     interactive
    0.53
     graphics
    0.52
     Unix
    0.52
     tele
    0.50
     Bildschirm
    0.49
    disk
    0.49
    Activations Density 1.133%

    No Known Activations