© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9183
    Prev
    Next
    INDEX
    Explanations

    modal verbs and expressions indicating possibility or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     khi
    -0.35
     vanden
    -0.34
     élé
    -0.32
     vieill
    -0.31
    ंदु
    -0.30
     avenir
    -0.30
     lorsqu
    -0.28
     matin
    -0.28
     modern
    -0.27
     prochain
    -0.27
    POSITIVE LOGITS
    +#+#
    0.84
     AssemblyCompany
    0.82
    iſchen
    0.79
     الحره
    0.73
     imagui
    0.73
    ロウィン
    0.71
     ſeine
    0.71
    iſche
    0.70
     Geiſt
    0.70
    principalColumn
    0.69
    Activations Density 0.422%

    No Known Activations