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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13060
    Prev
    Next
    INDEX
    Explanations

    Java data structures and classes related to I/O operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     оригіналу
    -0.73
    دانشنامهٔ
    -0.62
    AndEndTag
    -0.60
    Билгалдахарш
    -0.60
     препратки
    -0.60
     ◄
    -0.58
    Посилання
    -0.57
    maketitle
    -0.57
     lenker
    -0.57
    adaptiveStyles
    -0.56
    POSITIVE LOGITS
    irent
    0.44
    onoi
    0.43
     suffit
    0.42
    SourceChecksum
    0.42
    тня
    0.41
    PyExc
    0.41
    ArrowToggle
    0.41
     sich
    0.41
     timeval
    0.40
    elor
    0.40
    Activations Density 0.037%

    No Known Activations