© 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. 10-GEMMASCOPE-RES-16K
    6. 1781
    Prev
    Next
    INDEX
    Explanations

    mentions of rights, legal documents, and associated terms regarding accountability and entitlements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.72
    igshid
    -0.68
     Semoga
    -0.66
    abatic
    -0.66
    ñana
    -0.61
    dersfield
    -0.60
    gatron
    -0.58
    pearing
    -0.58
    odeon
    -0.57
    orsal
    -0.57
    POSITIVE LOGITS
    Personendaten
    0.73
    rungsseite
    0.64
     resourceCulture
    0.56
    IActionResult
    0.50
     PropTypes
    0.50
     existência
    0.49
    AnimationsModule
    0.49
    BeginContext
    0.47
    apimachinery
    0.46
    CharField
    0.46
    Activations Density 0.627%

    No Known Activations