Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14088
    Prev
    Next
    INDEX
    Explanations

    terms related to trading and finance

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

    Indonesian prefixes "men", "me", "meny", or "meng"

    np_acts-logits-general · gemini-2.0-flash

    Indonesian verb prefixes and English job titles

    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
     Portanto
    -0.55
     Espec
    -0.54
    ğından
    -0.50
     Jurí
    -0.49
     sienta
    -0.49
     Além
    -0.48
     coats
    -0.47
    ktı
    -0.46
     Aplica
    -0.46
    fg
    -0.45
    POSITIVE LOGITS
     men
    0.84
     me
    0.68
     meny
    0.65
     meng
    0.65
     meli
    0.64
     mera
    0.63
     meme
    0.63
     Men
    0.61
     memb
    0.60
     mer
    0.60
    Activations Density 0.019%

    No Known Activations