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. 14576
    Prev
    Next
    INDEX
    Explanations

    urgent calls to action and promotional offers

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

    Imperative sentences and calls to action

    np_acts-logits-general · gemini-2.0-flash

    act early

    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
    ycznego
    -0.57
     المعيارى
    -0.57
    ycznej
    -0.53
     Reverso
    -0.52
    Abit
    -0.51
    wachsenen
    -0.49
    aitu
    -0.47
    blica
    -0.47
    chmal
    -0.47
    omeness
    -0.47
    POSITIVE LOGITS
     hurry
    1.14
     act
    0.95
    early
    0.94
     Hurry
    0.93
     early
    0.93
     EARLY
    0.92
    Early
    0.91
    Hurry
    0.91
     acted
    0.88
     Early
    0.87
    Activations Density 0.234%

    No Known Activations