© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13696
    Prev
    Next
    INDEX
    Explanations

    references to the JSON content type and related media types in code or data exchanges

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

    "application/json"

    np_acts-logits-general · gemini-2.0-flash

    application/json content type

    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
    GEBURTSDATUM
    -0.71
     дописавши
    -0.69
     CreateTagHelper
    -0.57
     nahilalakip
    -0.56
    SourceChecksum
    -0.56
    msgTypes
    -0.54
    Obrázky
    -0.52
    ыгана
    -0.51
    Rüyada
    -0.51
    IntentFilter
    -0.51
    POSITIVE LOGITS
    json
    0.54
     nhật
    0.54
    hold
    0.50
    nitř
    0.49
    mendations
    0.49
    schmidt
    0.48
    etlen
    0.48
    etron
    0.48
     xml
    0.47
    ography
    0.47
    Activations Density 0.145%

    No Known Activations