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

    Neuronpedia

    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. 3880
    Prev
    Next
    INDEX
    Explanations

    elements of code related to data storage and management structures

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

    Followed by "._" or "~3~"

    np_acts-logits-general · gemini-2.0-flash

    storage._

    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
    ($_
    -0.58
    [_
    -0.58
    -
    -0.56
     &_
    -0.56
     [_
    -0.55
     {_
    -0.54
    _{\
    -0.53
    }_{\
    -0.52
     !_
    -0.51
    (&_
    -0.51
    POSITIVE LOGITS
    Personensuche
    0.92
    styleType
    0.92
    تقاوى
    0.90
     Paglinawan
    0.89
     EconPapers
    0.89
     estekak
    0.84
     BoxFit
    0.77
     Photocase
    0.77
    SequentialGroup
    0.76
    Cyfeiriadau
    0.75
    Activations Density 0.447%

    No Known Activations