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. 14-GEMMASCOPE-RES-16K
    6. 2930
    Prev
    Next
    INDEX
    Explanations

    SQL queries and database interaction code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     linkovi
    -0.71
    XmlAccessType
    -0.68
    Geplaatst
    -0.64
     pinulongan
    -0.63
    StoryboardSegue
    -0.62
    ⓧ
    -0.59
    Enllaços
    -0.59
    رشف
    -0.57
     препратки
    -0.56
    Istorija
    -0.55
    POSITIVE LOGITS
    onViewCreated
    0.69
    ExecuteReader
    0.69
    ResultSet
    0.65
    executeQuery
    0.65
    prepareStatement
    0.60
    ftagPool
    0.58
    usermodel
    0.55
    expandindo
    0.53
     jdbcTemplate
    0.51
    WriteLiteral
    0.51
    Activations Density 0.056%

    No Known Activations