© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 13902
    Prev
    Next
    INDEX
    Explanations

    instances of the word "activation" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    balho
    -0.68
     notes
    -0.65
    likes
    -0.63
     dto
    -0.61
     Stringer
    -0.60
    QTY
    -0.59
     Myles
    -0.58
    oughby
    -0.58
    ELTS
    -0.58
    pessoa
    -0.57
    POSITIVE LOGITS
     McCulloch
    1.00
     purpoſe
    0.97
     Activate
    0.96
     pleaſure
    0.93
     Activated
    0.93
     Toujours
    0.93
     tremp
    0.92
     Jefus
    0.92
    ization
    0.90
     Activ
    0.90
    Activations Density 0.135%

    No Known Activations