© 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. 24-GEMMASCOPE-RES-16K
    11. 2992
    Prev
    Next
    INDEX
    Explanations

    themes related to questioning and absurdity in statements

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

    "it" followed by "sounds"

    np_acts-logits-general · gemini-2.0-flash

    easier than it sounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gynhyrchwyd
    -0.79
    gypti
    -0.55
    HomeAsUpEnabled
    -0.51
     jspb
    -0.51
    IonicModule
    -0.50
     ویکی‌پدی
    -0.50
    σθαι
    -0.50
    tidaknya
    -0.49
    <thead>
    -0.48
     Italijani
    -0.48
    POSITIVE LOGITS
     sounds
    3.83
     sound
    3.71
     Sounds
    3.37
     SOUND
    3.37
    Sounds
    3.33
    sounds
    3.32
    sound
    3.30
     sounded
    3.27
     Sound
    3.19
    Sound
    3.14
    Activations Density 0.279%

    No Known Activations