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. 18-GEMMASCOPE-RES-16K
    6. 3690
    Prev
    Next
    INDEX
    Explanations

    statements related to performance and reliability in processes or products

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

    Preceding "right," "time," or words pertaining to correctness

    np_acts-logits-general · gemini-2.0-flash

    get it right

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.79
    PerformLayout
    -0.76
    AndEndTag
    -0.73
     OFDb
    -0.70
     /\.(
    -0.70
    setVerticalGroup
    -0.69
    PropertyChanging
    -0.69
    出版年
    -0.65
     дописавши
    -0.65
    extAlignment
    -0.65
    POSITIVE LOGITS
     first
    0.99
    first
    0.88
     pertama
    0.82
     første
    0.78
     primeira
    0.76
    Eerste
    0.74
     FIRST
    0.73
     первого
    0.71
    First
    0.71
     primera
    0.71
    Activations Density 0.181%

    No Known Activations