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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 9873
    Prev
    Next
    INDEX
    Explanations

    information related to naming and honoring individuals or entities

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

    Things being named after people or places

    np_acts-logits-general · gemini-2.0-flash

    named in honour of

    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
    setVerticalGroup
    -0.56
    styleType
    -0.54
     Botox
    -0.43
     externi
    -0.42
    ContentAsync
    -0.40
     ivelany
    -0.40
    хьтан
    -0.39
     cerro
    -0.39
     Приступљено
    -0.39
    chability
    -0.39
    POSITIVE LOGITS
     named
    1.94
     Named
    1.86
    named
    1.82
    Named
    1.76
     honour
    1.65
     honor
    1.56
     naming
    1.44
     honoring
    1.42
     homenagem
    1.28
     Honour
    1.26
    Activations Density 0.200%

    No Known Activations