© 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. 19-GEMMASCOPE-RES-16K
    11. 1773
    Prev
    Next
    INDEX
    Explanations

    code-related structures, particularly those involving access modifiers and method declarations in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ges
    -0.52
    ようです
    -0.51
    はじめに
    -0.49
    setDo
    -0.48
     min
    -0.45
     گذشت
    -0.45
     World
    -0.45
     Lav
    -0.44
    istos
    -0.44
    hiti
    -0.43
    POSITIVE LOGITS
    final
    2.06
     final
    1.93
     FINAL
    1.39
    Final
    1.31
    FINAL
    1.30
     Final
    1.24
     finally
    1.19
     finalised
    1.16
     finais
    1.12
     Finalmente
    1.10
    Activations Density 0.061%

    No Known Activations