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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15908
    Prev
    Next
    INDEX
    Explanations

    references to significant events or changes impacting individuals or communities, particularly involving health, governance, or social issues

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

    before "in"

    np_acts-logits-general · gemini-2.0-flash

    news events and situations

    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
     للاسماء
    -0.78
    SPATH
    -0.72
     '\\;'
    -0.71
    ."),
    -0.70
     appunto
    -0.69
    ContentAsync
    -0.68
     approximately
    -0.67
    hereinafter
    -0.67
    ),),
    -0.66
    masalahan
    -0.66
    POSITIVE LOGITS
     '
    1.15
     ‘
    1.13
     govt
    0.94
    govt
    0.68
    ...:
    0.68
     Govt
    0.67
    ‘
    0.66
     ':
    0.66
    </h1>
    0.66
     amid
    0.65
    Activations Density 0.188%

    No Known Activations