© 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 - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2225
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming concepts, particularly related to data structures and protocols

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

    Code related to enums, types, or modes

    np_acts-logits-general · gemini-2.0-flash

    enum 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
    AccessorTable
    -0.59
    atrici
    -0.57
     hostages
    -0.56
     counsels
    -0.56
     cuckoo
    -0.54
    Coordonnées
    -0.53
    gants
    -0.53
     ciphertext
    -0.53
    gdala
    -0.52
     $_(
    -0.52
    POSITIVE LOGITS
     type
    1.56
     mode
    1.49
    mode
    1.33
    type
    1.25
    Mode
    1.21
     kind
    1.18
     types
    1.18
     tipo
    1.17
     Mode
    1.15
    类型
    1.14
    Activations Density 0.729%

    No Known Activations