© 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. 18-GEMMASCOPE-RES-16K
    6. 9724
    Prev
    Next
    INDEX
    Explanations

    references to the English language

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

    "English"

    np_acts-logits-general · gemini-2.0-flash

    english language and culture

    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
    NameInMap
    -0.66
    دانشنامهٔ
    -0.64
     lenker
    -0.62
    DockStyle
    -0.60
    esinde
    -0.59
     &___
    -0.57
    VON
    -0.56
    CodeAttribute
    -0.56
    ="'.$
    -0.56
     Федерации
    -0.55
    POSITIVE LOGITS
     ENGLISH
    0.89
     anglaise
    0.83
     engl
    0.82
     English
    0.81
    ENGLISH
    0.78
     Engl
    0.75
     inglesa
    0.73
     Inggris
    0.73
     England
    0.72
     ENGLAND
    0.72
    Activations Density 0.109%

    No Known Activations