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. 23-GEMMASCOPE-RES-16K
    6. 11333
    Prev
    Next
    INDEX
    Explanations

    statements or remarks made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.81
    Geplaatst
    -0.79
    SuspendLayout
    -0.75
     NDEBUG
    -0.72
    دانشنامهٔ
    -0.71
     оригіналу
    -0.65
     feroit
    -0.62
     nahilalakip
    -0.62
    StoryboardSegue
    -0.62
     AssemblyCulture
    -0.62
    POSITIVE LOGITS
     bluntly
    0.79
    ,“
    0.79
     sarcas
    0.77
     wry
    0.77
     omin
    0.77
     thus
    0.76
    ,“
    0.72
    ,”
    0.72
     simply
    0.69
    ,"
    0.69
    Activations Density 0.234%

    No Known Activations