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. 12661
    Prev
    Next
    INDEX
    Explanations

    information related to names and their meanings, particularly those that are unisex or derived from different cultures

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

    names or surnames

    np_acts-logits-general · gemini-2.0-flash

    name and surname identification

    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
    ########.
    -0.92
     transfieras
    -0.76
     ivelany
    -0.68
     AssemblyCompany
    -0.68
    MENAFN
    -0.66
    Tembelea
    -0.66
     صوتيه
    -0.65
    adpleegd
    -0.64
    RenderAtEndOf
    -0.63
    findpost
    -0.60
    POSITIVE LOGITS
     surname
    1.03
     name
    0.98
     names
    0.96
     surnames
    0.84
     Names
    0.83
    surname
    0.80
    names
    0.78
     Name
    0.78
    Surname
    0.75
    name
    0.74
    Activations Density 0.195%

    No Known Activations