© 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. 14904
    Prev
    Next
    INDEX
    Explanations

    references to data fields and parameters in code or data structures

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

    Variable assignments to "null"

    np_acts-logits-general · gemini-2.0-flash

    variations of null

    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
    eadas
    -0.45
    sti
    -0.44
    ēj
    -0.44
     heng
    -0.44
    åde
    -0.44
    bete
    -0.43
    VERY
    -0.42
     meta
    -0.42
     間
    -0.41
    istin
    -0.41
    POSITIVE LOGITS
     null
    2.24
    null
    1.95
    Null
    1.36
     Null
    1.36
     NULL
    1.23
    NULL
    1.04
     nul
    0.93
     None
    0.91
     nulla
    0.87
     nullptr
    0.85
    Activations Density 0.059%

    No Known Activations