© 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. 20-GEMMASCOPE-RES-65K
    11. 2079
    Prev
    Next
    INDEX
    Explanations

    elements related to programming scripts and technical instructions

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

    custom mods and updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TextInputType
    -0.72
    ])){
    -0.66
    MemoryWarning
    -0.64
     ::=
    -0.64
    uxxxx
    -0.63
    ArrowToggle
    -0.61
     />);
    -0.59
    makeConstraints
    -0.56
     Redacción
    -0.55
    ">{{$
    -0.55
    POSITIVE LOGITS
     mod
    0.82
     modded
    0.77
     modified
    0.77
     custom
    0.76
     mods
    0.75
     files
    0.73
     Custom
    0.72
    compatible
    0.71
     compatible
    0.68
     updated
    0.67
    Activations Density 0.224%

    No Known Activations