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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-GEMMASCOPE-RES-16K
    6. 13693
    Prev
    Next
    INDEX
    Explanations

    concepts related to effectiveness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lähteet
    -0.51
    telegram
    -0.49
     RoutedEventArgs
    -0.49
     Zuw
    -0.48
     TORT
    -0.47
    zung
    -0.46
    нились
    -0.46
    xaml
    -0.45
     razu
    -0.45
    StructField
    -0.45
    POSITIVE LOGITS
     effective
    4.39
    effective
    4.08
     Effective
    4.01
    Effective
    3.95
     EFFECTIVE
    3.51
     effectiveness
    2.95
     ineffective
    2.75
     efficace
    2.74
    ffective
    2.72
     efektif
    2.68
    Activations Density 0.103%

    No Known Activations