© 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. 7-GEMMASCOPE-RES-16K
    11. 14958
    Prev
    Next
    INDEX
    Explanations

    passive voice constructions and instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 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
    principalColumn
    -0.60
     CommonModule
    -0.58
     queſta
    -0.57
     reaſon
    -0.56
     Theſe
    -0.55
    Ƚ
    -0.54
    Населення
    -0.54
     fédé
    -0.54
     ſtand
    -0.54
     GenerationType
    -0.52
    POSITIVE LOGITS
    anti
    0.38
    олові
    0.37
     必
    0.37
     الحره
    0.35
    新たに
    0.33
    lle
    0.33
    WS
    0.32
     gainera
    0.31
    ++)
    0.31
    KS
    0.30
    Activations Density 0.525%

    No Known Activations