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. 12-GEMMASCOPE-RES-16K
    6. 10228
    Prev
    Next
    INDEX
    Explanations

    references to the act of calling, whether in terms of phone calls or making requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Endian
    -0.83
     Paisley
    -0.80
     embargo
    -0.78
    wendi
    -0.74
    acen
    -0.74
     Milne
    -0.74
     Plage
    -0.73
     Elsie
    -0.72
    ưỡng
    -0.69
     busted
    -0.69
    POSITIVE LOGITS
     CALL
    1.85
     call
    1.83
     Call
    1.77
    CALL
    1.73
     calls
    1.72
     Calls
    1.72
    Call
    1.66
    Calls
    1.64
    call
    1.63
    calls
    1.58
    Activations Density 0.116%

    No Known Activations