© 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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 3237
    Prev
    Next
    INDEX
    Explanations

    terms and references related to the Flash multimedia platform and its components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.96
    principalTable
    -0.94
    IndentedString
    -0.87
    ISupport
    -0.86
    expandindo
    -0.85
    ⓧ
    -0.82
     propOrder
    -0.80
    TagMode
    -0.80
    googleapis
    -0.78
     تانيه
    -0.78
    POSITIVE LOGITS
     flash
    1.19
    flash
    1.14
     Flash
    1.12
    Flash
    1.04
     FLASH
    1.03
    FLASH
    0.95
     flashes
    0.84
     flashed
    0.84
     flas
    0.81
    flas
    0.71
    Activations Density 0.137%

    No Known Activations