© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30087
    Prev
    Next
    INDEX
    Explanations

    instructions or requests for reading and responding to documentation or comments

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

    read the listing

    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
     off
    -0.48
     sue
    -0.46
     ster
    -0.45
     ter
    -0.45
     int
    -0.45
     turn
    -0.44
    lam
    -0.44
     str
    -0.43
     ث
    -0.42
    kegaard
    -0.42
    POSITIVE LOGITS
    +#+#
    0.91
     specialmente
    0.88
     suivants
    0.83
    URLException
    0.82
     ComVisible
    0.80
     seguenti
    0.79
     almeno
    0.78
    UnusedPrivate
    0.78
    featureID
    0.76
     nahilalakip
    0.75
    Activations Density 0.091%

    No Known Activations