© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 10205
    Prev
    Next
    INDEX
    Explanations

    references to background settings in design or layout contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coloring
    -0.36
    Stderr
    -0.35
    색
    -0.35
    Triangle
    -0.35
    colored
    -0.35
    Colored
    -0.35
     colored
    -0.34
     colour
    -0.34
     color
    -0.34
     farb
    -0.34
    POSITIVE LOGITS
    UrlResolution
    0.64
    RegistryLite
    0.54
     repeat
    0.54
    Repeat
    0.54
     referenties
    0.52
    PerformLayout
    0.51
    setupUi
    0.51
     Repeat
    0.50
     repeats
    0.50
    XmlAccessType
    0.49
    Activations Density 0.004%

    No Known Activations