© 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. 12-GEMMASCOPE-RES-16K
    6. 13642
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs, particularly those starting with "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trä
    -0.39
     EXHIB
    -0.30
     bruja
    -0.29
     béné
    -0.28
     muchacha
    -0.27
    Bakgrunnsstoff
    -0.27
     isIn
    -0.26
     Syrie
    -0.26
     Fuerzas
    -0.26
     odeur
    -0.26
    POSITIVE LOGITS
     ब्रेकडाउन
    0.81
     To
    0.70
    titleMargin
    0.66
     щоб
    0.66
     جهت
    0.65
     мәкал
    0.64
     чтобы
    0.63
    ########.
    0.63
    Portale
    0.62
    verwijspagina
    0.62
    Activations Density 0.623%

    No Known Activations