Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1070
    Prev
    Next
    INDEX
    Explanations

    terms related to vehicle performance and specifications

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

    phrases related to vehicle performance and driving modes

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

    engine tuning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.63
    actus
    -0.56
     renewal
    -0.56
    TargetException
    -0.52
     <>",
    -0.52
     bambou
    -0.49
     Renewal
    -0.49
     GENERATED
    -0.48
    arche
    -0.48
     Jehovah
    -0.48
    POSITIVE LOGITS
     dyno
    0.89
     tune
    0.78
     tunes
    0.71
     tuner
    0.71
    tune
    0.69
     tuning
    0.68
    Tune
    0.66
     Tuning
    0.66
     Tune
    0.66
    Tuning
    0.65
    Activations Density 0.028%

    No Known Activations