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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-GEMMASCOPE-RES-16K
    6. 8658
    Prev
    Next
    INDEX
    Explanations

    snippets of code and programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -1.01
    PerformLayout
    -0.89
     تانيه
    -0.76
    TypedDataSet
    -0.73
    mybatisplus
    -0.72
    UserScript
    -0.70
    出版年
    -0.68
    Rhestr
    -0.68
    kuuta
    -0.65
     LoginComponent
    -0.63
    POSITIVE LOGITS
     use
    0.40
     kull
    0.40
     AssemblyCulture
    0.40
     declarado
    0.40
    patine
    0.39
     nacionais
    0.37
     skriver
    0.37
     pesquisas
    0.37
    циали
    0.37
    kadot
    0.36
    Activations Density 1.219%

    No Known Activations