Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11950
    Prev
    Next
    INDEX
    Explanations

    specific types of biological or technical references related to genetics and medical terminology

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

    Abbreviations and initialisms

    np_acts-logits-general · gemini-2.0-flash

    biological molecules and computing components

    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
    ings
    -0.59
    ess
    -0.58
    ening
    -0.57
    bar
    -0.57
     Compañ
    -0.55
    новниш
    -0.55
    enskap
    -0.55
    waite
    -0.54
    mste
    -0.53
    inig
    -0.53
    POSITIVE LOGITS
     AssemblyCulture
    0.83
    躇
    0.81
    ablanca
    0.80
    IContainer
    0.80
     GoogleFonts
    0.77
    rrggbb
    0.77
     betweenstory
    0.69
    ajuku
    0.67
    thâu
    0.66
    copal
    0.65
    Activations Density 0.851%

    No Known Activations