© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 12710
    Prev
    Next
    INDEX
    Explanations

    instances of the word "used" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -1.14
     doInBackground
    -1.02
    styleType
    -0.99
     propOrder
    -0.97
    ChildScrollView
    -0.95
    tagHelperRunner
    -0.94
    InputBorder
    -0.93
     getItemId
    -0.91
    ########.
    -0.91
    QMetaType
    -0.90
    POSITIVE LOGITS
     use
    1.21
     used
    1.08
     Used
    0.99
    used
    0.93
    use
    0.88
    Used
    0.88
     Use
    0.84
     uses
    0.81
     USED
    0.80
     usar
    0.78
    Activations Density 0.290%

    No Known Activations