© 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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2808
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data related to health metrics

    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
    Autoritní
    -0.47
    >({
    -0.36
    [__
    -0.35
     fhew
    -0.34
    gesteld
    -0.34
     OFDb
    -0.34
     verantwoorde
    -0.34
    WIDE
    -0.33
     Powerful
    -0.33
     puissante
    -0.33
    POSITIVE LOGITS
     propOrder
    0.73
    URLException
    0.68
     '\\;'
    0.67
     isComment
    0.58
    发表于
    0.57
    躇
    0.56
    msgTypes
    0.54
    blockList
    0.54
     للمعارف
    0.53
    KommentareTeilen
    0.51
    Activations Density 1.520%

    No Known Activations