© 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. 18-GEMMASCOPE-RES-16K
    6. 8176
    Prev
    Next
    INDEX
    Explanations

    actions related to cessation or prohibition

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

    Actions being stopped or canceled

    np_acts-logits-general · gemini-2.0-flash

    stop altogether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trotzdem
    -0.57
    weile
    -0.53
     dennoch
    -0.52
    ="@+
    -0.50
    riedenheit
    -0.50
    estimators
    -0.49
    urezza
    -0.49
    postmedia
    -0.49
     LoggerFactory
    -0.47
    CELLANEOUS
    -0.47
    POSITIVE LOGITS
     altogether
    0.79
    AddTagHelper
    0.74
    すべての
    0.69
    一切
    0.68
    全ての
    0.67
     wszel
    0.66
     entirely
    0.65
     kaikki
    0.63
     👎
    0.63
     unprofitable
    0.63
    Activations Density 0.548%

    No Known Activations