© 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. 2971
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that involve significant numbers or organizations related to various sectors

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

    following commas

    np_acts-logits-general · gemini-2.0-flash

    common articles after punctuation

    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
    utnik
    -0.63
     gehabt
    -0.62
     فريبيس
    -0.61
    tonode
    -0.61
    ább
    -0.60
    uties
    -0.56
     ddelweddau
    -0.56
     kasarigan
    -0.55
     sobra
    -0.53
    bkz
    -0.52
    POSITIVE LOGITS
     which
    1.17
     a
    1.04
     an
    0.98
    which
    0.90
     sebuah
    0.87
     což
    0.74
    formerly
    0.73
     μια
    0.71
     formerly
    0.68
     وهي
    0.67
    Activations Density 0.389%

    No Known Activations