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. 13764
    Prev
    Next
    INDEX
    Explanations

    references to political dynamics and voter sentiments

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

    avoidance or dismissal

    np_acts-logits-general · gemini-2.0-flash

    avoidance and dismissal

    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
     AssemblyProduct
    -0.62
     AssertionError
    -0.57
    foria
    -0.55
    bodyParser
    -0.53
     SEDS
    -0.52
     >=",
    -0.51
    存于互联网档案馆
    -0.50
    تقاوى
    -0.49
     BoxFit
    -0.48
    seman
    -0.48
    POSITIVE LOGITS
     avoidance
    1.02
     avoid
    0.97
    Avoid
    0.97
     fuir
    0.96
     avoided
    0.95
     Avoid
    0.94
     AVOID
    0.94
    avoid
    0.92
     rechazo
    0.92
     shun
    0.91
    Activations Density 0.349%

    No Known Activations