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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2708
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements, particularly those related to program flow control such as conditionals and return statements

    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
    Empereur
    -0.55
    ^{-}\
    -0.52
    halla
    -0.51
    {§
    -0.49
    υτό
    -0.48
     interactiva
    -0.48
    buro
    -0.46
    ządu
    -0.46
    nione
    -0.46
    tifkan
    -0.46
    POSITIVE LOGITS
     if
    1.02
    if
    0.88
     when
    0.80
     AspNetCore
    0.80
     AssemblyCompany
    0.77
     nếu
    0.77
     dacă
    0.72
    Personensuche
    0.72
    FieldBuilder
    0.72
    StoryboardSegue
    0.72
    Activations Density 0.074%

    No Known Activations