© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 428
    Prev
    Next
    INDEX
    Explanations

    architectural attributes and specifications of buildings

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

    building facade and exterior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    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
    -0.75
     المعيارى
    -0.63
     kasarigan
    -0.54
     drin
    -0.52
     ekos
    -0.52
    يكب
    -0.49
    yntaxException
    -0.49
    تفصیلات
    -0.48
     upo
    -0.48
    vgili
    -0.48
    POSITIVE LOGITS
     facade
    0.74
     façade
    0.70
     facades
    0.68
     exterior
    0.66
     faç
    0.59
     front
    0.54
     stucco
    0.53
     building
    0.52
     gable
    0.52
     Exterior
    0.52
    Activations Density 0.018%

    No Known Activations