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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 60626
    Prev
    Next
    INDEX
    Explanations

    references to architectural elements and their descriptions

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

    building facade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.46
    imageshack
    -0.45
    findpost
    -0.44
    opcional
    -0.44
    uroy
    -0.44
    Pairs
    -0.44
     Italijanski
    -0.43
     мәкал
    -0.41
    tonode
    -0.41
    限り
    -0.41
    POSITIVE LOGITS
     facade
    0.81
     façade
    0.77
     fachada
    0.75
     facades
    0.69
     фаса
    0.60
     exterior
    0.58
    exterior
    0.57
    Exterior
    0.57
     Exterior
    0.56
     faç
    0.54
    Activations Density 0.040%

    No Known Activations