© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 3745
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols used in expressions or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.77
    دانشنامهٔ
    -0.71
     bezeichneter
    -0.70
    medriver
    -0.67
    msgTypes
    -0.66
     kaarangay
    -0.64
    Rohy
    -0.63
    ByVersion
    -0.63
    AnimationsModule
    -0.63
    XmlEnum
    -0.61
    POSITIVE LOGITS
    left
    1.21
    <b>
    0.74
    <strong>
    0.70
    Left
    0.65
    LEFT
    0.64
     left
    0.63
     betrekking
    0.63
    <em>
    0.62
    <i>
    0.61
     Left
    0.60
    Activations Density 0.137%

    No Known Activations