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. 15779
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and coding concepts

    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
     Audiodateien
    -0.69
    ConstraintMaker
    -0.68
     snippetHide
    -0.67
     للاسماء
    -0.63
     referrerpolicy
    -0.63
    PerformLayout
    -0.62
     AppModule
    -0.62
    PageRoute
    -0.61
    XtraEditors
    -0.61
    IndentedString
    -0.60
    POSITIVE LOGITS
    ing
    0.54
     them
    0.53
    SEGUIR
    0.49
    ficulty
    0.49
    viate
    0.48
    celled
    0.47
    atak
    0.47
    ³)
    0.47
    '});
    0.46
    merkung
    0.46
    Activations Density 0.921%

    No Known Activations