© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102689
    Prev
    Next
    INDEX
    Explanations

    details related to the structure and contents of a multi-volume work or set

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

    volumes and discs

    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
     disambiguazione
    -0.49
    tagHelperRunner
    -0.44
     fairies
    -0.43
     Autorisations
    -0.42
     intérprete
    -0.42
    Halloween
    -0.38
    Сообщение
    -0.38
    unknownFields
    -0.37
    汰
    -0.37
     consommate
    -0.37
    POSITIVE LOGITS
    الدراسه
    0.56
    Autoritní
    0.55
    JScrollPane
    0.54
     informée
    0.51
     volumes
    0.50
     pages
    0.50
    RTGC
    0.49
     Volumes
    0.49
     books
    0.47
    Pages
    0.46
    Activations Density 0.019%

    No Known Activations