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. 16-GEMMASCOPE-RES-16K
    6. 8929
    Prev
    Next
    INDEX
    Explanations

    quantifiable metrics related to health statistics and economic performance

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

    Expressing numerical rankings and dominance

    np_acts-logits-general · gemini-2.0-flash

    leading, largest, No. 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    small
    -0.65
     small
    -0.65
     modest
    -0.62
    Small
    -0.59
    fäl
    -0.56
     moderately
    -0.55
     lesser
    -0.55
    tiny
    -0.54
     Entry
    -0.54
     tiny
    -0.53
    POSITIVE LOGITS
     dominance
    0.78
     dominant
    0.74
    makeConstraints
    0.71
     dominating
    0.70
     dominante
    0.70
     DOMIN
    0.68
    dominant
    0.66
     dominate
    0.65
     насељу
    0.64
     dominates
    0.63
    Activations Density 0.218%

    No Known Activations