© 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. 25-GEMMASCOPE-RES-16K
    11. 607
    Prev
    Next
    INDEX
    Explanations

    specific actions and processes related to document handling and retrieval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.68
    ParallelGroup
    -0.54
    évaluateur
    -0.53
    脚注の使い方
    -0.53
    ROLS
    -0.50
     standstill
    -0.49
    visionnement
    -0.49
    queryInterface
    -0.49
    таратура
    -0.48
    Espèce
    -0.48
    POSITIVE LOGITS
     store
    0.93
     resell
    0.87
     storing
    0.80
     revend
    0.79
     Store
    0.79
     menyimpan
    0.79
    STORE
    0.78
    store
    0.76
     nahilalakip
    0.76
     STORE
    0.75
    Activations Density 0.476%

    No Known Activations