© 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. 20-GEMMASCOPE-RES-131K
    6. 123546
    Prev
    Next
    INDEX
    Explanations

    references to image files and operations related to images

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

    image file names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.54
     సౌకర్య
    -0.49
    олові
    -0.47
    aarrggbb
    -0.47
    reactstrap
    -0.46
    хьтан
    -0.46
    StructEnd
    -0.46
     MainAxisSize
    -0.46
    策
    -0.45
    tawesome
    -0.44
    POSITIVE LOGITS
     photographs
    0.51
     photo
    0.51
     photographic
    0.49
     photograph
    0.48
     images
    0.47
     Photographic
    0.47
     image
    0.45
     photography
    0.44
    photo
    0.44
     imageName
    0.44
    Activations Density 0.007%

    No Known Activations