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. 21-GEMMASCOPE-RES-16K
    6. 7079
    Prev
    Next
    INDEX
    Explanations

    legal and procedural terminology in relation to web design and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '))
    
    -0.81
    '
    
    -0.76
    }))
    
    -0.69
    !")
    
    -0.67
    ;");
    -0.66
    ()");
    -0.65
    .")
    
    -0.65
    ')")
    -0.64
    '])
    
    -0.63
    .");
    
    -0.62
    POSITIVE LOGITS
    ”?
    0.90
     beginnetje
    0.79
    )?
    0.78
     oprot
    0.78
    »?
    0.75
    AddTagHelper
    0.74
    styleable
    0.72
    "?
    0.70
    Personensuche
    0.68
    addCriterion
    0.68
    Activations Density 1.572%

    No Known Activations