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. 3033
    Prev
    Next
    INDEX
    Explanations

    explicit references to film and television production and character discussions

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

    Movie or TV show references

    np_acts-logits-general · gemini-2.0-flash

    shows seasons or episodes

    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
    Personensuche
    -0.94
    ientí
    -0.64
    randomUUID
    -0.62
     KML
    -0.59
     متعلقه
    -0.58
     wireType
    -0.57
     Проци
    -0.57
    uxxxx
    -0.57
    
    -0.57
     CanadaChoose
    -0.57
    POSITIVE LOGITS
    《
    1.27
     《
    1.04
     The
    0.94
    <i>
    0.94
    『
    0.93
    <em>
    0.92
     『
    0.85
     ‘
    0.79
    :《
    0.78
    textit
    0.76
    Activations Density 1.187%

    No Known Activations