© 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. 12-GEMMASCOPE-RES-16K
    6. 1686
    Prev
    Next
    INDEX
    Explanations

    references to server-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kies
    -0.52
    RectangleBorder
    -0.46
     Fokus
    -0.44
     Croce
    -0.43
    sum
    -0.42
     Pio
    -0.42
    pick
    -0.41
     Pasquale
    -0.41
     DIY
    -0.41
    bmp
    -0.41
    POSITIVE LOGITS
     Server
    1.73
     server
    1.66
     Servers
    1.52
    Server
    1.52
     SERVER
    1.47
    server
    1.43
     servers
    1.38
    getServer
    1.28
    SERVER
    1.28
     serveur
    1.27
    Activations Density 0.135%

    No Known Activations