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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2981
    Prev
    Next
    INDEX
    Explanations

    indicators of treatment effectiveness in healthcare contexts

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

    Followed by a bullet point

    np_acts-logits-general · gemini-2.0-flash

    sociales, debido, these

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    WithIOException
    -1.06
    InjectAttribute
    -0.78
    出版年
    -0.77
    ValueStyle
    -0.76
    InstrumentedTest
    -0.72
    /***/
    -0.68
     ivelany
    -0.67
    yntaxException
    -0.65
    AutoScaleMode
    -0.65
    LikeLike
    -0.64
    POSITIVE LOGITS
    ↵↵
    0.65
    *
    0.54
     Sociales
    0.48
      
    0.48
    addGap
    0.47
     Debido
    0.46
    These
    0.45
    лети
    0.43
    iltà
    0.43
     These
    0.43
    Activations Density 0.090%

    No Known Activations