© 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
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 10970
    Prev
    Next
    INDEX
    Explanations

    key attributes and advantages related to items, topics, or individuals

    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
    -0.58
    oneofs
    -0.48
    NAF
    -0.46
    styleType
    -0.44
     bf
    -0.42
    TIA
    -0.42
    Xaml
    -0.41
    exitRule
    -0.41
    MigrationBuilder
    -0.41
    naf
    -0.40
    POSITIVE LOGITS
     especially
    0.60
     vooral
    0.59
     hlavně
    0.58
     zwłaszcza
    0.57
     especialmente
    0.57
     szczególnie
    0.57
     soprattutto
    0.55
     surtout
    0.54
    devším
    0.54
     specialmente
    0.53
    Activations Density 0.406%

    No Known Activations