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. 3938
    Prev
    Next
    INDEX
    Explanations

    programming structures related to object-oriented programming concepts, such as classes and methods

    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
    GraphicsUnit
    -0.96
    SequentialGroup
    -0.95
    basicConfig
    -0.72
    __*/
    -0.71
    NewUrlParser
    -0.70
    +#+
    -0.70
     pinulongan
    -0.68
    ButtonModule
    -0.68
     VIAF
    -0.66
    StoryboardSegue
    -0.64
    POSITIVE LOGITS
    rungsseite
    0.78
    homonymie
    0.69
    ródło
    0.58
    contentLoaded
    0.55
    ьаж
    0.55
     المعيارى
    0.54
    queryInterface
    0.53
    expandindo
    0.52
    曖昧さ回避
    0.52
    -------------</
    0.49
    Activations Density 0.153%

    No Known Activations