© 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. 4-GEMMASCOPE-RES-16K
    11. 15768
    Prev
    Next
    INDEX
    Explanations

    occurrences of phrases related to endings or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.65
    ANDUM
    -0.65
     autorytatywna
    -0.62
     فريبيس
    -0.59
    Autoritní
    -0.56
    IsMutable
    -0.55
    Identyfik
    -0.54
    migrationBuilder
    -0.53
    LookAnd
    -0.50
    @[+][
    -0.49
    POSITIVE LOGITS
     akhir
    1.02
     end
    1.01
     ends
    0.97
     completion
    0.97
     endTime
    0.96
     finish
    0.96
     ending
    0.95
     finis
    0.95
     نهاية
    0.95
     termination
    0.94
    Activations Density 0.810%

    No Known Activations