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. 25-GEMMASCOPE-RES-16K
    6. 7934
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and syntax rules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saites
    -0.70
    forChild
    -0.66
     חיצוניים
    -0.63
     calendriers
    -0.56
    openzeppelin
    -0.52
    ineno
    -0.51
    ReusableCell
    -0.51
    
    -0.50
    DialogContent
    -0.49
    íqu
    -0.49
    POSITIVE LOGITS
     capital
    1.48
     Upper
    1.41
     upper
    1.38
    Upper
    1.37
     Capital
    1.37
     UPPER
    1.33
     lowercase
    1.33
     Lower
    1.33
    capital
    1.33
    Capital
    1.33
    Activations Density 0.563%

    No Known Activations