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. 5-GEMMASCOPE-RES-16K
    6. 2566
    Prev
    Next
    INDEX
    Explanations

    definitions and instances of models and data structures commonly used in programming

    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
     /\.(
    -0.90
    "])
    
    -0.69
    ")));
    
    -0.69
    "):
    
    -0.67
    HomeAsUp
    -0.66
    "]).
    -0.66
     '/')
    -0.65
     /\.
    -0.64
    '):
    
    -0.64
    '))
    
    -0.64
    POSITIVE LOGITS
    Dto
    0.90
    dto
    0.85
    DTO
    0.82
     dto
    0.80
    usermodel
    0.71
    payload
    0.66
    DTOs
    0.63
     DTO
    0.58
    Dtos
    0.57
    fastjson
    0.57
    Activations Density 0.126%

    No Known Activations