© 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. 3-GEMMASCOPE-RES-16K
    11. 6352
    Prev
    Next
    INDEX
    Explanations

    words that express clarity or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.93
     Guadalupe
    -0.72
     Marsden
    -0.68
    WebMethod
    -0.67
    giphy
    -0.67
     Thrones
    -0.66
     Bevan
    -0.65
    щением
    -0.65
     SECT
    -0.63
    yntaxException
    -0.63
    POSITIVE LOGITS
     clearly
    2.96
    clearly
    2.70
     Clearly
    2.57
    Clearly
    2.41
     CLEAR
    1.98
     clear
    1.97
     claramente
    1.97
     clairement
    1.86
     chiaramente
    1.77
     duidelijk
    1.69
    Activations Density 0.051%

    No Known Activations