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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-GEMMASCOPE-RES-16K
    6. 13701
    Prev
    Next
    INDEX
    Explanations

    references to code elements and identifiers in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flashdata
    -0.73
    abstractmethod
    -0.70
    RenderAtEndOf
    -0.69
    rawDesc
    -0.66
    "])
    
    -0.65
    DeleteBehavior
    -0.63
    ]]
    
    -0.62
     photolibrary
    -0.62
    eradish
    -0.60
    !")
    
    -0.60
    POSITIVE LOGITS
    CL
    1.11
    cl
    1.04
     CL
    1.01
     cl
    0.91
    cls
    0.84
     estekak
    0.72
    outer
    0.67
     cls
    0.66
    GR
    0.66
    cli
    0.65
    Activations Density 0.077%

    No Known Activations