Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11611
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to medical conditions, treatments, and their physiological impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.30
     valable
    -0.30
     tellement
    -0.30
    ActionCreators
    -0.29
     rubia
    -0.28
     amargo
    -0.28
    ServletContext
    -0.27
    ValueGenerated
    -0.27
    SupportActionBar
    -0.27
     استنادى
    -0.27
    POSITIVE LOGITS
    ConstraintMaker
    0.76
     دیکھیے
    0.76
    ſelf
    0.75
     EconPapers
    0.72
    yntaxException
    0.72
     للمعارف
    0.71
    rungsseite
    0.66
    MessageOf
    0.66
     समीक्षाओं
    0.65
     vooz
    0.65
    Activations Density 1.251%

    No Known Activations