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. 7474
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data compression and file formats

    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
    elemField
    -0.68
    AccessorTable
    -0.60
     Exactos
    -0.57
    spesies
    -0.53
     }{@
    -0.52
    TextWatcher
    -0.51
    rester
    -0.47
    cheidung
    -0.47
     Typing
    -0.47
     ORCH
    -0.47
    POSITIVE LOGITS
     compression
    1.23
     compressed
    1.14
     Compression
    1.09
     compress
    1.06
    压缩
    1.06
    compression
    0.99
     zip
    0.98
    Zip
    0.98
    Compression
    0.97
     Zip
    0.97
    Activations Density 0.390%

    No Known Activations