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. 5901
    Prev
    Next
    INDEX
    Explanations

    terms related to semiconductor manufacturing and imaging technologies

    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
    ftagPool
    -0.58
    󠁬
    -0.52
    :✨
    -0.50
    VersionUID
    -0.46
    CardHeader
    -0.46
    atshirt
    -0.45
     informée
    -0.44
    monials
    -0.43
     Taktlose
    -0.43
    MLLoader
    -0.43
    POSITIVE LOGITS
     precision
    0.72
     accuracy
    0.66
     quality
    0.64
     précision
    0.62
    precision
    0.62
    Precision
    0.60
     Precision
    0.60
     PRECISION
    0.59
    精度
    0.58
     качество
    0.56
    Activations Density 1.155%

    No Known Activations