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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15229
    Prev
    Next
    INDEX
    Explanations

    technical parameters related to system configuration and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    WebElementEntity
    -0.57
     MainAxisSize
    -0.54
    Spoljašnje
    -0.53
     виправивши
    -0.52
    setupUi
    -0.52
    jsonwebtoken
    -0.50
    Legături
    -0.49
     allAfrica
    -0.49
    skab
    -0.48
    jak
    -0.48
    POSITIVE LOGITS
     read
    1.10
     reads
    0.99
     write
    0.95
     reading
    0.95
     READ
    0.93
     Reads
    0.88
     Read
    0.88
     Write
    0.86
    read
    0.85
    write
    0.82
    Activations Density 0.584%

    No Known Activations