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. 16-GEMMASCOPE-RES-16K
    6. 6412
    Prev
    Next
    INDEX
    Explanations

    key political and governmental concepts related to qualifications and competences

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

    Uncommon punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    speculative theology, telegrams, reconciliation

    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
     meaningfully
    -0.77
     sourced
    -0.73
     minimally
    -0.70
     surreal
    -0.69
     flipped
    -0.68
     Jefus
    -0.68
    mahaman
    -0.68
    etheless
    -0.67
     envisioned
    -0.66
     hooves
    -0.66
    POSITIVE LOGITS
     enfans
    0.85
     employés
    0.73
     employé
    0.71
     giebt
    0.70
     habitudes
    0.69
     spéciaux
    0.69
     réunions
    0.68
    AndEndTag
    0.68
     brano
    0.66
    <bos>
    0.64
    Activations Density 1.348%

    No Known Activations