© 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. 25-GEMMASCOPE-RES-16K
    11. 1312
    Prev
    Next
    INDEX
    Explanations

    trends related to changes in statistics or data values, particularly in the context of drug arrests and financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.72
     الحره
    -0.70
    AnchorTagHelper
    -0.68
     المعيارى
    -0.68
     TextAppearance
    -0.67
    RectangleBorder
    -0.65
     HasFactory
    -0.64
    RenderAtEndOf
    -0.63
    الحياه
    -0.61
     חיצוניים
    -0.60
    POSITIVE LOGITS
     sharply
    0.84
     rapidly
    0.81
     steeply
    0.74
     precipit
    0.72
     faster
    0.72
     steadily
    0.71
     dramatically
    0.71
     tajam
    0.66
     exponentially
    0.61
     meteor
    0.60
    Activations Density 0.337%

    No Known Activations