© 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. 5-GEMMASCOPE-RES-16K
    11. 3177
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols, notations, and operations commonly used in formal equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     er
    -0.50
     du
    -0.50
    buc
    -0.49
    ragment
    -0.49
    ****************
    -0.48
    ougou
    -0.48
    ButtonModule
    -0.47
     b
    -0.47
    File
    -0.46
     пла
    -0.46
    POSITIVE LOGITS
    mapStateToProps
    0.81
     myſelf
    0.80
     itſelf
    0.78
     Majefty
    0.78
    parsedMessage
    0.77
     poffible
    0.75
     houſe
    0.75
    Personendaten
    0.75
    aarrggbb
    0.74
     nvm
    0.73
    Activations Density 1.172%

    No Known Activations