© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2514
    Prev
    Next
    INDEX
    Explanations

    negative outcomes or critiques related to data handling and implementations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical, software, databases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    rrggbb
    -0.76
    ]--;
    -0.75
    GeneratedValue
    -0.72
    XmlAccessorType
    -0.71
    nodoc
    -0.69
    السكان
    -0.69
    WebServlet
    -0.69
    Portail
    -0.68
     kasarigan
    -0.67
    saraba
    -0.66
    POSITIVE LOGITS
    item
    0.60
     الحره
    0.56
    interopRequire
    0.47
    tabular
    0.47
    itemize
    0.45
    toxicity
    0.42
    newline
    0.42
    quiti
    0.41
     Trenton
    0.41
    λευ
    0.39
    Activations Density 0.003%

    No Known Activations