© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15414
    Prev
    Next
    INDEX
    Explanations

    phrases related to health conditions and treatments

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

    Punctuation followed by a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    start of new sentences

    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
    )";
    
    -0.72
     AssemblyCulture
    -0.70
    wpi
    -0.70
     nahilalakip
    -0.69
    LookAnd
    -0.69
    orneys
    -0.69
    muerzo
    -0.67
    IUrlHelper
    -0.67
     SafeMath
    -0.64
     lenker
    -0.63
    POSITIVE LOGITS
    Apart
    1.06
    Nowadays
    1.01
    Moreover
    1.01
     Apart
    1.00
     Nowadays
    0.98
     Moreover
    0.96
     Beside
    0.90
    Besides
    0.87
     nowadays
    0.86
     Besides
    0.85
    Activations Density 0.406%

    No Known Activations