© 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. 9587
    Prev
    Next
    INDEX
    Explanations

    references to technology and media consumption in relation to social behavior

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

    Follows "of" or relates to modern technology

    np_acts-logits-general · gemini-2.0-flash

    advances in digital technology

    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
    enumi
    -0.71
     traditionnels
    -0.70
     nahilalakip
    -0.68
     <<<<<<<<<<<<<<
    -0.68
    oa̍t
    -0.66
    lüssel
    -0.65
    tahankan
    -0.62
     للاسماء
    -0.60
    yntaxException
    -0.59
     historiques
    -0.59
    POSITIVE LOGITS
     modern
    1.34
    modern
    1.14
     technology
    1.12
     computerized
    1.12
     Internet
    1.08
     electronic
    1.07
     computer
    1.07
     internet
    1.07
     digital
    1.07
     moderna
    1.05
    Activations Density 0.683%

    No Known Activations