© 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. 12217
    Prev
    Next
    INDEX
    Explanations

    specific names or terms related to various biological entities or types of studies

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

    Tokens starting with "Bil", "Sil", "Gil" or "il"

    np_acts-logits-general · gemini-2.0-flash

    Bil, Sil, Gil prefixes

    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
    ed
    -0.72
    omock
    -0.64
     trời
    -0.57
    ngdoc
    -0.55
    ERAS
    -0.54
    ities
    -0.51
    cademia
    -0.51
    mapreduce
    -0.48
    ONSO
    -0.48
    ي
    -0.48
    POSITIVE LOGITS
    #+#
    0.80
     فريبيس
    0.63
     Zil
    0.59
    licon
    0.57
     PIL
    0.56
    UnsafeEnabled
    0.56
     LIL
    0.56
    lean
    0.55
     utafitiHapana
    0.55
     BIL
    0.54
    Activations Density 0.105%

    No Known Activations