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

    Neuronpedia

    Jacobian LensNEW
    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. 22-GEMMASCOPE-RES-16K
    11. 16144
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals, particularly those with military or entertainment backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -1.03
    iſchen
    -0.87
     Geſch
    -0.84
    IntoConstraints
    -0.83
    niſſe
    -0.81
     laſſen
    -0.80
    ſchaft
    -0.80
    httphttps
    -0.77
     estekak
    -0.76
    rungsseite
    -0.75
    POSITIVE LOGITS
    /
    0.35
    2
    0.34
    IT
    0.34
    ])),
    0.34
    _
    0.33
    (
    0.32
    WE
    0.32
    ,
    0.32
     zaś
    0.31
    0
    0.31
    Activations Density 0.673%

    No Known Activations