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. 1937
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and their attributes in code

    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
    GEBURTSDATUM
    -1.02
    ()]);
    -0.91
    }*/
    
    -0.86
    ']))
    
    -0.83
    twimg
    -0.83
    ConstraintMaker
    -0.82
     betweenstory
    -0.82
     referenties
    -0.80
    "]));
    -0.79
     препратки
    -0.78
    POSITIVE LOGITS
    UIFont
    0.56
     IBOutlet
    0.55
     Rami
    0.55
     Byr
    0.51
     كومونز
    0.51
     voz
    0.50
     Primo
    0.50
     Haupts
    0.49
    uj
    0.49
     र
    0.49
    Activations Density 0.029%

    No Known Activations