© 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. 16-GEMMASCOPE-RES-65K
    11. 30669
    Prev
    Next
    INDEX
    Explanations

    the presence of opening or starting markers in a structured document

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

    categories, names, and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    th
    -0.57
    p
    -0.54
    u
    -0.53
    B
    -0.53
    lan
    -0.53
    U
    -0.53
    ky
    -0.52
    ka
    -0.52
    ha
    -0.52
    est
    -0.51
    POSITIVE LOGITS
     pinulongan
    0.98
     Réponses
    0.83
    المناصب
    0.81
    Tikang
    0.80
    featureID
    0.79
     الحره
    0.79
     '\\;'
    0.78
    ")));
    0.77
    GIVEREF
    0.76
    ptonshire
    0.76
    Activations Density 0.006%

    No Known Activations