© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101843
    Prev
    Next
    INDEX
    Explanations

    segments related to scripting or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Superhost
    -0.83
    __':
    -0.75
     BoxFit
    -0.75
    __":
    -0.74
     समीक्षक
    -0.74
     queſta
    -0.70
    niſſe
    -0.70
    ChildScrollView
    -0.70
    onAttach
    -0.69
    enablog
    -0.69
    POSITIVE LOGITS
    ///</
    0.35
    </
    0.27
    ガ
    0.26
    ########.
    0.26
    <h3>
    0.26
    就
    0.25
    ↵
    0.25
     jueves
    0.24
    mo
    0.24
    <i>
    0.23
    Activations Density 0.175%

    No Known Activations