© 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. 10-GEMMASCOPE-RES-16K
    11. 12439
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to pre-event processes and planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.87
    KommentareTeilen
    -0.86
    bolista
    -0.83
    '>"
    -0.83
    wisata
    -0.83
    
    -0.81
    rigation
    -0.81
     Wallflower
    -0.81
    zoek
    -0.81
    }{*}{}
    -0.80
    POSITIVE LOGITS
    Pre
    1.67
     PRE
    1.59
     Pre
    1.54
    PRE
    1.52
    pre
    1.46
     pre
    1.42
     pré
    1.21
     Pré
    1.14
     Pref
    1.14
    PreExecute
    1.12
    Activations Density 0.152%

    No Known Activations