© 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-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 13672
    Prev
    Next
    INDEX
    Explanations

    the word "stand" and its variations in various contexts, indicating a focus on positions or actions related to standing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.83
     muualla
    -0.65
    RegressionTest
    -0.64
    الحياه
    -0.64
    featureID
    -0.62
     CID
    -0.61
    rrggbb
    -0.57
    phazard
    -0.56
    AddTagHelper
    -0.56
     BytesLike
    -0.55
    POSITIVE LOGITS
     stand
    2.39
     STAND
    2.28
     standing
    2.23
     Stand
    2.23
    Stand
    2.09
     stands
    2.08
     stood
    2.06
     Standing
    1.98
    Standing
    1.94
     Stands
    1.90
    Activations Density 0.107%

    No Known Activations