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. 11194
    Prev
    Next
    INDEX
    Explanations

    terms related to accessibility roles in web development

    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
     Wilber
    -0.61
     refusé
    -0.52
    шње
    -0.50
    ๊ะ
    -0.50
     lontano
    -0.50
    fällig
    -0.49
    javadoc
    -0.49
    пати
    -0.49
    kumar
    -0.49
    ذ
    -0.49
    POSITIVE LOGITS
     aria
    3.12
    Aria
    1.88
     Aria
    1.84
    aria
    1.83
     ARIA
    1.67
    ARIA
    1.64
    ariah
    0.97
     Arias
    0.94
    ària
    0.93
    arias
    0.91
    Activations Density 0.019%

    No Known Activations