© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 6763
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical inference and data processing techniques in Apache libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     serons
    -0.50
    jaciół
    -0.49
     fez
    -0.48
    schirm
    -0.47
    ob
    -0.47
     Store
    -0.44
    خصة
    -0.44
    Биография
    -0.43
    ్రామ
    -0.43
     dinam
    -0.43
    POSITIVE LOGITS
    \}\\
    0.88
    IsMutable
    0.84
     jLabel
    0.76
    ſelves
    0.74
    RegressionTest
    0.74
     Autorizaciones
    0.73
     jScrollPane
    0.73
     Stamp
    0.71
    VIAF
    0.70
    ſelf
    0.70
    Activations Density 1.930%

    No Known Activations