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. 11-GEMMASCOPE-RES-16K
    6. 5764
    Prev
    Next
    INDEX
    Explanations

    references to values and attributes in data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Superhosts
    -0.85
    AnchorStyles
    -0.80
     ISNI
    -0.79
    Tembelea
    -0.78
    )<\
    -0.74
    RLock
    -0.73
     *)(
    -0.73
    }:${
    -0.72
     дописавши
    -0.72
    "):
    
    -0.70
    POSITIVE LOGITS
     values
    1.62
     value
    1.54
     VALUE
    1.46
     Value
    1.46
     Values
    1.46
    VALUE
    1.46
    Value
    1.45
    value
    1.42
    values
    1.36
    Values
    1.27
    Activations Density 0.122%

    No Known Activations