Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 2792
    Prev
    Next
    INDEX
    Explanations

    code structure and programming constructs related to data types and versioning

    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
    AndEndTag
    -0.61
    emlrt
    -0.60
    oredCriteria
    -0.57
     setuptools
    -0.55
    Życiorys
    -0.54
    攷
    -0.54
     poveznice
    -0.52
     Dumnezeu
    -0.48
     raping
    -0.47
    Distribuzione
    -0.47
    POSITIVE LOGITS
    \{\\
    0.71
     ***!
    0.69
     arşivlendi
    0.67
    )))),
    0.66
     وتسجيلات
    0.65
     AttributeSet
    0.64
     MessageBoxIcon
    0.62
     StatelessWidget
    0.59
    usermodel
    0.58
    Xna
    0.58
    Activations Density 0.013%

    No Known Activations