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. 5-GEMMASCOPE-RES-16K
    6. 13775
    Prev
    Next
    INDEX
    Explanations

    attributes related to visibility and position in programming code

    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
     AssemblyTitle
    -0.79
     виправивши
    -0.73
     GetEnumerator
    -0.68
    antMatchers
    -0.68
    sidemargin
    -0.65
    GEBURTSDATUM
    -0.64
     '{@
    -0.63
    Архівовано
    -0.63
    الدراسه
    -0.62
     JpaRepository
    -0.62
    POSITIVE LOGITS
     يتيمه
    0.59
     تضيفلها
    0.59
     незавершена
    0.54
    ⋱
    0.53
    таратура
    0.53
     ComVisible
    0.52
    copic
    0.47
    inį
    0.47
    vää
    0.46
    ">*</
    0.45
    Activations Density 0.030%

    No Known Activations