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. 7502
    Prev
    Next
    INDEX
    Explanations

    structural and functional elements in programming code

    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
    isfile
    -0.54
     mati
    -0.48
    +:+
    -0.47
    addCriterion
    -0.46
    Демографія
    -0.46
    ]})
    -0.45
    Chham
    -0.44
     коды
    -0.43
     Schofield
    -0.43
    nyttet
    -0.43
    POSITIVE LOGITS
     sizeof
    1.76
    sizeof
    1.70
    SIZ
    0.80
    offsetof
    0.75
    strlen
    0.72
     size
    0.69
    Size
    0.69
     strlen
    0.66
    size
    0.65
     length
    0.63
    Activations Density 0.294%

    No Known Activations