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. 1465
    Prev
    Next
    INDEX
    Explanations

    names and familial relationships of individuals

    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
    PMailer
    -0.63
     pari
    -0.47
     law
    -0.46
    UUUU
    -0.46
    ikit
    -0.45
    uuuu
    -0.44
    openssl
    -0.43
     зу
    -0.43
    ọn
    -0.43
     CHtml
    -0.43
    POSITIVE LOGITS
     Paglinawan
    0.77
     unknownFields
    0.74
     '\\;'
    0.71
    исленность
    0.70
     aikana
    0.69
     resourceCulture
    0.69
     tárgy
    0.68
     referenties
    0.66
     <>",
    0.66
     समीक्षाओं
    0.65
    Activations Density 0.036%

    No Known Activations