© 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. 18-GEMMASCOPE-RES-16K
    11. 8294
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, and punctuation related to historical references

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

    years

    np_acts-logits-general · gemini-2.0-flash

    1812, 1849, 1852, 1907

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.92
     purpoſe
    -0.91
     itſelf
    -0.90
    Portály
    -0.88
    NUMX
    -0.87
     pleaſure
    -0.83
     Jefus
    -0.82
     himſelf
    -0.79
     Monfieur
    -0.78
     cauſe
    -0.74
    POSITIVE LOGITS
     muß
    0.66
     mußte
    0.59
     ибо
    0.57
     wußte
    0.57
     mengadakan
    0.55
     müßte
    0.54
     furent
    0.53
    createServer
    0.53
     folosi
    0.51
     evidently
    0.49
    Activations Density 0.463%

    No Known Activations