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. 11920
    Prev
    Next
    INDEX
    Explanations

    references to compatibility and incompatibility 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 @ 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
    fficio
    -0.64
    hassee
    -0.56
    damento
    -0.55
    کز
    -0.54
    ETERS
    -0.54
    pric
    -0.52
     Sexton
    -0.52
     Burke
    -0.51
    ḷ
    -0.51
    cendental
    -0.51
    POSITIVE LOGITS
     compatible
    1.88
     compatibility
    1.83
     Compatible
    1.81
    compatible
    1.80
     COMPAT
    1.79
     Compatibility
    1.77
    Compatible
    1.69
     incompatible
    1.66
    compatibility
    1.66
    COMPAT
    1.64
    Activations Density 0.176%

    No Known Activations