© 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. 12290
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate specific situational contexts or conditions

    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
     Pingback
    -0.74
    脚注の使い方
    -0.73
    RSpec
    -0.73
    pyplot
    -0.67
    Dav
    -0.67
     Spartans
    -0.67
     Tallahassee
    -0.65
     rapp
    -0.64
     initComponents
    -0.64
     Crisp
    -0.63
    POSITIVE LOGITS
    Under
    1.75
     Under
    1.73
     under
    1.73
    under
    1.67
    UNDER
    1.67
     UNDER
    1.64
    neath
    1.53
     Underwood
    1.32
    Bajo
    1.28
     unter
    1.26
    Activations Density 0.143%

    No Known Activations