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. 5-GEMMASCOPE-RES-16K
    6. 2688
    Prev
    Next
    INDEX
    Explanations

    references to data structures in programming, particularly those associated with "phone books" and games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PostExecute
    -0.64
    webElementXpaths
    -0.63
    UnknownFields
    -0.63
    onActivityResult
    -0.61
     configureStore
    -0.61
     createSlice
    -0.61
    LayoutInflater
    -0.60
    steamcommunity
    -0.60
     createStore
    -0.58
    assertRaises
    -0.58
    POSITIVE LOGITS
    KommentareTeilen
    0.74
     Ahor
    0.61
    TacToe
    0.53
     متعلقه
    0.52
    MigrationBuilder
    0.52
     Winaray
    0.52
     CURIAM
    0.51
    ależ
    0.51
    UnitTesting
    0.50
     Shallow
    0.49
    Activations Density 0.348%

    No Known Activations