© 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. 17-GEMMASCOPE-RES-16K
    11. 9304
    Prev
    Next
    INDEX
    Explanations

    references to the United States and related entities or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tanleria
    -0.83
    клопе
    -0.70
     lenker
    -0.66
    bootstrapcdn
    -0.59
    ########.
    -0.59
    gwt
    -0.59
    jsonwebtoken
    -0.58
    FieldBuilder
    -0.57
     endblock
    -0.57
    InjectAttribute
    -0.57
    POSITIVE LOGITS
    kus
    0.55
     Us
    0.55
     Kus
    0.52
    atoday
    0.51
     Huse
    0.50
     dollar
    0.50
     användas
    0.50
     Usman
    0.50
    UAGE
    0.49
     Cus
    0.49
    Activations Density 0.243%

    No Known Activations