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. 12078
    Prev
    Next
    INDEX
    Explanations

    questions and references to identity and existence

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

    "Who" at the beginning of a phrase/question

    np_acts-logits-general · gemini-2.0-flash

    who questions

    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
    ItemBackground
    -0.73
    PreferredItem
    -0.70
     Meksiku
    -0.67
    awtextra
    -0.66
    expandindo
    -0.65
    SharedCtor
    -0.64
    OrNil
    -0.63
     مشين
    -0.62
     ivelany
    -0.61
     Uniti
    -0.61
    POSITIVE LOGITS
     Who
    0.99
    Who
    0.96
     who
    0.92
    who
    0.79
    Quién
    0.70
     whom
    0.68
    誰
    0.68
     antaranya
    0.68
     誰
    0.67
    Quem
    0.67
    Activations Density 0.089%

    No Known Activations