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. 25-GEMMASCOPE-RES-16K
    6. 4379
    Prev
    Next
    INDEX
    Explanations

    content related to influential figures and their contributions in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.80
    webElementXpaths
    -0.78
    kháu
    -0.73
    OGND
    -0.73
    DockStyle
    -0.72
     Roskov
    -0.70
    StoryboardSegue
    -0.69
     виправивши
    -0.68
     ویکی‌پدی
    -0.66
     صوتيه
    -0.65
    POSITIVE LOGITS
     iconic
    1.37
     icon
    1.28
     icons
    1.27
     legendary
    1.16
    iconic
    1.16
     legend
    1.11
     timeless
    1.11
    Iconic
    1.09
     Iconic
    1.06
     classic
    1.05
    Activations Density 0.317%

    No Known Activations