© 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. 1006
    Prev
    Next
    INDEX
    Explanations

    questions and phrases focused on the concept of "how."

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

    Comes after "how" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    degree or surprise expressed with "how"

    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
    Personensuche
    -0.58
    nteral
    -0.53
     Référence
    -0.47
    XSSF
    -0.46
    ágos
    -0.45
     entière
    -0.43
     szolg
    -0.43
    μεν
    -0.42
    <bos>
    -0.42
     neutralization
    -0.42
    POSITIVE LOGITS
     much
    0.93
     incredibly
    0.84
     amazing
    0.82
     Administrativna
    0.78
     lucky
    0.78
     awesome
    0.78
     far
    0.77
     they
    0.74
     incredible
    0.74
     "..\..\..\
    0.73
    Activations Density 0.062%

    No Known Activations