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. 6521
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts related to molecular structure and analysis

    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
    expandindo
    -0.54
     BoxFit
    -0.54
    Naissance
    -0.51
    Aud
    -0.49
     garden
    -0.47
     osob
    -0.47
     кӀ
    -0.46
     shooter
    -0.46
     Aud
    -0.46
    otechnical
    -0.45
    POSITIVE LOGITS
     structure
    0.92
     Structure
    0.89
    Structure
    0.84
     crystal
    0.82
     structures
    0.80
     structural
    0.80
    structure
    0.78
     conformation
    0.77
    PDB
    0.77
     Structural
    0.76
    Activations Density 1.310%

    No Known Activations