© 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. 11566
    Prev
    Next
    INDEX
    Explanations

    the presence of specific control sequences or markers in structured data

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

    Precedes a colon

    np_acts-logits-general · gemini-2.0-flash

    scientific or technical terms

    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
    -
    -1.08
     
    -1.08
    ,
    -1.00
     “
    -0.97
    .
    -0.94
     and
    -0.86
     "
    -0.84
     on
    -0.83
     in
    -0.83
     (
    -0.82
    POSITIVE LOGITS
     يتيمه
    1.76
     незавершена
    1.75
    Datuak
    1.58
     الحره
    1.53
     pinulongan
    1.49
     autorytatywna
    1.48
     المعيارى
    1.46
    rungsseite
    1.45
    تقاوى
    1.45
     ſind
    1.38
    Activations Density 0.047%

    No Known Activations