© 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. 20-GEMMASCOPE-RES-16K
    11. 3398
    Prev
    Next
    INDEX
    Explanations

    instances of negation in conditions

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

    "!" followed by certain code-related terms

    np_acts-logits-general · gemini-2.0-flash

    if not

    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
    NewLabel
    -0.61
     não
    -0.52
    LOYE
    -0.50
    السكان
    -0.49
    '};
    -0.48
     not
    -0.47
    Nuorodos
    -0.46
     most
    -0.46
     "";
    -0.45
    Trama
    -0.44
    POSITIVE LOGITS
     مرئيه
    0.83
    protoimpl
    0.78
    HasBeenSet
    0.66
    Hozzáférés
    0.64
    isValid
    0.64
    ьаж
    0.64
     pysty
    0.63
    didSet
    0.63
     }}"></
    0.63
    تقاوى
    0.62
    Activations Density 0.029%

    No Known Activations