© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5320
    Prev
    Next
    INDEX
    Explanations

    stylish formatting or visual style attributes in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ("}");
    -0.64
    IonicModule
    -0.59
     externi
    -0.55
    meteries
    -0.54
    ніципалі
    -0.52
    parsedMessage
    -0.52
    äsident
    -0.51
     utafitiHapana
    -0.51
     PrintWriter
    -0.50
    selves
    -0.50
    POSITIVE LOGITS
     souple
    0.62
    Autoritní
    0.61
    writerow
    0.60
     sī
    0.59
     /\.
    0.59
    chner
    0.59
    classnames
    0.58
     CONCEP
    0.57
    dzić
    0.57
    cshtml
    0.57
    Activations Density 0.028%

    No Known Activations