© 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. 33-GEMMASCOPE-RES-16K
    11. 11267
    Prev
    Next
    INDEX
    Explanations

    options and settings related to user preferences in a digital context

    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
     ब्रेकडाउन
    -0.34
    argout
    -0.33
     Verpflichtung
    -0.27
    body
    -0.24
     Geschle
    -0.23
    protoimpl
    -0.22
     пройти
    -0.22
     Aérea
    -0.21
     brengt
    -0.21
    nd
    -0.21
    POSITIVE LOGITS
     settings
    2.75
     Settings
    2.39
    settings
    2.27
    Settings
    2.16
     SETTINGS
    2.08
     setting
    2.00
    設定
    1.80
    SETTINGS
    1.80
    setting
    1.78
     configuration
    1.76
    Activations Density 1.224%

    No Known Activations