© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27737
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions for action or requirements for participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    before the, time of, wherever you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     domestiques
    -0.44
     كندا
    -0.43
     görüş
    -0.41
     personali
    -0.41
     guantes
    -0.41
    uma
    -0.41
     gerekti
    -0.40
    둘
    -0.40
     ApiException
    -0.40
     principio
    -0.40
    POSITIVE LOGITS
    endphp
    0.96
     AssemblyProduct
    0.88
    مصادر
    0.81
    ImageContext
    0.81
    \{\\
    0.79
    Tikang
    0.77
    EndInit
    0.74
    PerformLayout
    0.74
    tagext
    0.70
    AddHtmlAttribute
    0.69
    Activations Density 0.038%

    No Known Activations