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. 18-GEMMASCOPE-RES-16K
    6. 1495
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to court proceedings and rulings

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

    Pronouns "they" or "them"

    np_acts-logits-general · gemini-2.0-flash

    they/them pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ويكيميديا
    -0.54
    timeScale
    -0.54
     resourceCulture
    -0.53
    visuel
    -0.52
    apimachinery
    -0.50
    apunov
    -0.50
    forName
    -0.49
     referenties
    -0.48
    titian
    -0.48
     %@",
    -0.48
    POSITIVE LOGITS
     they
    2.81
     them
    2.73
     They
    2.65
    They
    2.58
     mereka
    2.49
    they
    2.41
    Mereka
    2.20
     Mereka
    2.17
    them
    2.10
    彼らは
    2.09
    Activations Density 1.222%

    No Known Activations