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. 21-GEMMASCOPE-RES-16K
    6. 302
    Prev
    Next
    INDEX
    Explanations

    terms associated with inequality or disparity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.85
    typeparam
    -0.52
    AllowUser
    -0.51
    ávajú
    -0.49
     chi̍t
    -0.48
     Percival
    -0.48
    oust
    -0.47
    يست
    -0.47
     Belf
    -0.47
     مُعرِّف
    -0.46
    POSITIVE LOGITS
    rate
    1.08
    ate
    1.05
     rate
    1.00
    ates
    0.98
    ATE
    0.97
    RATE
    0.97
    ATES
    0.93
    Rate
    0.92
     ate
    0.91
     Rate
    0.90
    Activations Density 0.394%

    No Known Activations