© 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 - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5755
    Prev
    Next
    INDEX
    Explanations

    assertions of belief and personal opinion

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

    "mean" or "means"

    np_acts-logits-general · gemini-2.0-flash

    what something means

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.78
    fromnode
    -0.71
    AddTagHelper
    -0.71
    endphp
    -0.70
    qtype
    -0.65
    存于互联网档案馆
    -0.64
    yntaxException
    -0.62
    devamını
    -0.61
    ChildScrollView
    -0.61
    invokeLater
    -0.61
    POSITIVE LOGITS
     means
    3.40
     mean
    3.27
    means
    2.89
     Means
    2.75
     MEANS
    2.60
    mean
    2.60
     MEAN
    2.57
    Means
    2.57
     Mean
    2.56
    Mean
    2.37
    Activations Density 0.549%

    No Known Activations