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. 16-GEMMASCOPE-RES-16K
    6. 6502
    Prev
    Next
    INDEX
    Explanations

    elements related to digital media interactions and functions

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

    preceding specific function/purpose

    np_acts-logits-general · gemini-2.0-flash

    fashionable season

    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
    forName
    -0.62
     '\\;'
    -0.60
    Skocz
    -0.54
     aesthetically
    -0.54
     kosme
    -0.52
     Glor
    -0.52
     aesthetics
    -0.49
    BindView
    -0.49
    obraz
    -0.49
     Sexy
    -0.48
    POSITIVE LOGITS
     AssemblyCulture
    0.72
     ModelExpression
    0.67
    gées
    0.62
     تضيفلها
    0.61
    ostatic
    0.57
    WithContext
    0.57
     Internal
    0.54
     internal
    0.54
     Intern
    0.53
    antaine
    0.53
    Activations Density 1.637%

    No Known Activations