© 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. 16-GEMMASCOPE-RES-16K
    11. 11061
    Prev
    Next
    INDEX
    Explanations

    names or identifiers, likely related to individuals or entities

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

    Follows capitalized abbreviations

    np_acts-logits-general · gemini-2.0-flash

    Nunes, Housley, Hager, Cuthbertson

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    дравствуйте
    -0.55
    ,
    -0.53
     in
    -0.51
    Външни
    -0.51
     cote
    -0.51
    airobi
    -0.51
     }}"></
    -0.50
     prior
    -0.50
    lloworld
    -0.49
     sign
    -0.49
    POSITIVE LOGITS
    IUrlHelper
    0.96
    withstanding
    0.93
    itudinal
    0.85
     Pelop
    0.79
     getP
    0.79
    tably
    0.78
     purg
    0.78
     GenerationType
    0.76
     lèvres
    0.75
     Ys
    0.75
    Activations Density 0.644%

    No Known Activations