© 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. 7050
    Prev
    Next
    INDEX
    Explanations

    variables and coordinates used in programming or mathematics

    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
    tagHelperRunner
    -0.67
    expandindo
    -0.56
     Normdatei
    -0.55
    gucig
    -0.54
     Italijani
    -0.53
    elemField
    -0.53
     ostavi
    -0.51
     tartalomajánló
    -0.50
     Италијани
    -0.50
    ագրություններ
    -0.50
    POSITIVE LOGITS
     mouseY
    0.64
    clientY
    0.56
    scrollY
    0.54
     posY
    0.53
     height
    0.52
     y
    0.52
    gridy
    0.49
    minY
    0.49
    velocityY
    0.48
     yPos
    0.47
    Activations Density 0.233%

    No Known Activations