© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 25
    Prev
    Next
    INDEX
    Explanations

    words with specific morphological endings or suffixes typically associated with names or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.63
    ंदीखरीदारी
    -0.54
     tranſ
    -0.50
    utilisons
    -0.50
    findpost
    -0.49
    erweise
    -0.47
     Jefus
    -0.47
    //
    -0.47
     архивлан
    -0.46
     ſta
    -0.45
    POSITIVE LOGITS
     transférez
    0.37
    Agen
    0.36
    ga
    0.35
    pery
    0.35
    VIRGO
    0.34
    thene
    0.33
     userRepository
    0.33
     inflater
    0.32
    !*\
    0.32
    TokenName
    0.31
    Activations Density 0.304%

    No Known Activations