© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6870
    Prev
    Next
    INDEX
    Explanations

    references to societal issues, particularly concerning racial discrimination and the effects of social dynamics

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

    Followed by punctuation or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    especially, sometimes, particularly

    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
     protoimpl
    -0.78
    :✨
    -0.72
     للاسماء
    -0.71
    StructEnd
    -0.69
    rrggbb
    -0.67
     ModelExpression
    -0.66
    FieldBuilder
    -0.65
    sizeCache
    -0.59
     ویکی‌پدیای
    -0.59
    OGND
    -0.59
    POSITIVE LOGITS
     especially
    1.22
    Especially
    1.20
     Especially
    1.17
    especially
    1.15
    pecially
    0.97
     sometimes
    0.95
     especialmente
    0.94
     ESPEC
    0.94
     nowadays
    0.93
     particularly
    0.90
    Activations Density 0.550%

    No Known Activations