© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 16599
    Prev
    Next
    INDEX
    Explanations

    the verb "had" in various contexts, indicating past experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LLocation
    -0.87
     Olsson
    -0.82
     Ressources
    -0.81
    見えます
    -0.81
     Reuter
    -0.80
    atchewan
    -0.77
     Erscheinung
    -0.77
    woordig
    -0.77
     Torrey
    -0.76
    PreferredItem
    -0.74
    POSITIVE LOGITS
     Had
    1.19
     had
    1.17
     HAD
    1.16
    Had
    1.07
     earlier
    0.96
    Earlier
    0.94
    had
    0.90
     Earlier
    0.90
     hoped
    0.85
     originally
    0.84
    Activations Density 0.079%

    No Known Activations