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. 18-GEMMASCOPE-RES-16K
    6. 10242
    Prev
    Next
    INDEX
    Explanations

    keywords related to software engineering and programming concepts, particularly in Java and related frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    CURLOPT
    -0.56
    AddHtmlAttribute
    -0.53
    жели
    -0.52
    etcode
    -0.51
     hés
    -0.51
     estekak
    -0.51
    jspx
    -0.50
     Sự
    -0.49
    렵
    -0.49
     createSlice
    -0.49
    POSITIVE LOGITS
    Hauptartikel
    0.63
    core
    0.62
     framework
    0.61
     ErrIntOverflow
    0.60
     CommonModule
    0.60
     Chwiliwch
    0.59
    tvguidetime
    0.58
     continuant
    0.56
     Foundation
    0.56
     Framework
    0.55
    Activations Density 0.250%

    No Known Activations