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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 4659
    Prev
    Next
    INDEX
    Explanations

    references to measurements or calculations associated with profit margins in a business/legal context

    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
    Datuak
    -0.77
    ICIAS
    -0.67
     كومونز
    -0.65
    conditionally
    -0.63
     tölt
    -0.60
    nsk
    -0.59
    ENSITY
    -0.59
     OFDb
    -0.58
     profondément
    -0.58
     Gruber
    -0.56
    POSITIVE LOGITS
    arounds
    0.78
    onAttach
    0.73
     Waray
    0.70
     Cleanup
    0.70
     lockout
    0.69
    DebuggerNonUser
    0.68
     cutoff
    0.67
     Burnout
    0.67
    up
    0.67
     estoppel
    0.67
    Activations Density 0.267%

    No Known Activations