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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 1259
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "prototype"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cinfo
    -0.57
    fulness
    -0.54
     dokun
    -0.54
     enter
    -0.52
    beitet
    -0.50
     eux
    -0.48
    drops
    -0.48
     Enter
    -0.47
    hale
    -0.47
    hydrates
    -0.46
    POSITIVE LOGITS
    prototype
    1.07
    StoryboardSegue
    0.78
     ویکی‌پدیا
    0.73
    ngdoc
    0.72
    LookAnd
    0.69
    DockStyle
    0.68
    tagHelperRunner
    0.66
    出版年
    0.65
    EnableWeb
    0.62
     transfieras
    0.59
    Activations Density 0.099%

    No Known Activations