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. 22-GEMMASCOPE-RES-16K
    6. 14095
    Prev
    Next
    INDEX
    Explanations

    specific engineering and technical descriptions of structures and devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thâu
    -0.66
     ModelExpression
    -0.66
    webElement
    -0.63
     Meksiku
    -0.62
    !*\
    -0.61
    RegistryLite
    -0.60
    تفصیلات
    -0.56
    HideFlags
    -0.56
    PreExecute
    -0.55
     ComVisible
    -0.54
    POSITIVE LOGITS
     shape
    1.40
     shaped
    1.38
    shaped
    1.29
    haped
    1.17
    shape
    1.15
     Shaped
    1.12
     shapes
    1.08
     Shape
    1.05
     pattern
    1.03
     structure
    1.01
    Activations Density 0.758%

    No Known Activations