© 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. 9752
    Prev
    Next
    INDEX
    Explanations

    references to scientific concepts and terminology related to light and its effects

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

    light and optical properties

    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
     tra
    -0.29
    Tra
    -0.27
     tự
    -0.27
    Обо
    -0.26
     πέ
    -0.25
    ати
    -0.25
     echoed
    -0.25
    風
    -0.25
    bilden
    -0.25
    MY
    -0.25
    POSITIVE LOGITS
     photo
    0.92
     illumination
    0.86
     optical
    0.86
     Photo
    0.85
    photo
    0.84
     photos
    0.84
     wavelength
    0.83
     foto
    0.82
     light
    0.81
     Wavelength
    0.81
    Activations Density 0.166%

    No Known Activations