© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3489
    Prev
    Next
    INDEX
    Explanations

    present or past tense forms of "to be" and "to have"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ainfi
    -0.55
    ambién
    -0.43
     avoient
    -0.42
    ientras
    -0.41
     étoient
    -0.40
     feroit
    -0.40
    #![
    -0.40
     rodríguez
    -0.40
     informée
    -0.39
     ſche
    -0.39
    POSITIVE LOGITS
     Yates
    0.51
    Iam
    0.50
    __*/
    0.49
     Diam
    0.49
     Oso
    0.49
     capable
    0.48
     Prou
    0.48
    zut
    0.48
     Nay
    0.48
     Sil
    0.47
    Activations Density 0.496%

    No Known Activations