© 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. 11-GEMMASCOPE-RES-16K
    11. 1595
    Prev
    Next
    INDEX
    Explanations

    references to corporate strategies and business operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whilst
    -0.86
    Whilst
    -0.81
    非常的
    -0.80
     whilst
    -0.70
     wonderful
    -0.68
     we
    -0.66
    に於
    -0.65
     our
    -0.62
     /
    -0.61
     beautiful
    -0.60
    POSITIVE LOGITS
    addCriterion
    0.91
    TagMode
    0.90
     autorytatywna
    0.88
    drawSprites
    0.85
    ⓧ
    0.83
     NDEBUG
    0.81
     disambiguazione
    0.81
    ReusableCell
    0.80
     doubtnut
    0.80
     ifølge
    0.78
    Activations Density 0.602%

    No Known Activations