© 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. 22-GEMMASCOPE-RES-16K
    11. 565
    Prev
    Next
    INDEX
    Explanations

    phrases related to durability and performance under stress

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

    Occurrences after prepositions

    np_acts-logits-general · gemini-2.0-flash

    usage and wear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DispatchToProps
    -0.61
    protobuf
    -0.60
    getSystemService
    -0.59
    GraphicsUnit
    -0.59
    nestjs
    -0.58
    XmlAccessorType
    -0.58
    írus
    -0.55
    pushFollow
    -0.55
    zepte
    -0.54
     elettrica
    -0.54
    POSITIVE LOGITS
     wear
    1.07
     usage
    1.00
     daily
    0.94
     abuse
    0.89
     frequent
    0.85
     Usage
    0.83
     overuse
    0.82
     Repeated
    0.82
     użytk
    0.82
    usage
    0.81
    Activations Density 0.303%

    No Known Activations