© 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. 41-GEMMASCOPE-RES-16K
    11. 7343
    Prev
    Next
    INDEX
    Explanations

    references to physical positions and actions related to standing or being grounded

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.48
    interopRequire
    -0.47
     AssemblyCulture
    -0.44
    Portale
    -0.43
    GEBURTSDATUM
    -0.43
    PickerController
    -0.42
    DrawerToggle
    -0.40
    ProgressHUD
    -0.40
    awtextra
    -0.40
     المعيارى
    -0.40
    POSITIVE LOGITS
     ground
    3.95
    ground
    3.28
     Ground
    3.16
    Ground
    3.11
     GROUND
    3.08
    GROUND
    2.80
     grond
    2.19
     grounds
    2.09
    地面
    2.08
    grounds
    1.91
    Activations Density 0.690%

    No Known Activations