© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5818
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to regeneration or recovery

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

    after "re" or copyright symbol

    np_acts-logits-general · gemini-2.0-flash

    rewarding, reclusive, unrevealed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteBarrier
    -0.78
    contentLoaded
    -0.64
    numerusform
    -0.56
    omiast
    -0.56
    ########.
    -0.56
    StoreMessageInfo
    -0.55
    
    -0.54
    ValueStyle
    -0.54
    存于互联网档案馆
    -0.53
     وتسجيلات
    -0.53
    POSITIVE LOGITS
     descricao
    0.48
    ardless
    0.47
    ResponseEntity
    0.46
     cargas
    0.46
    utveck
    0.46
     règle
    0.45
    WritableDatabase
    0.44
     turn
    0.43
    GeneratedValue
    0.42
     вс
    0.42
    Activations Density 0.163%

    No Known Activations