© 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. 2805
    Prev
    Next
    INDEX
    Explanations

    references to automotive specifications and performance metrics

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

    Capitalized abbreviations or place names

    np_acts-logits-general · gemini-2.0-flash

    German cities and brands

    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
    TypedDataSet
    -0.74
    BeginContext
    -0.73
    SPATH
    -0.66
    ANTLR
    -0.65
    ViewFeatures
    -0.63
    存于互联网档案馆
    -0.59
    StoryboardSegue
    -0.59
     Evansville
    -0.59
     fondamental
    -0.59
     Volcan
    -0.59
    POSITIVE LOGITS
     BMW
    0.64
    BMW
    0.56
     Bav
    0.56
    bmw
    0.55
     bmw
    0.53
     Bavarian
    0.51
     Berlin
    0.51
     Munich
    0.50
    Berlin
    0.49
    bav
    0.48
    Activations Density 0.167%

    No Known Activations