© 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. 5-GEMMASCOPE-RES-16K
    11. 3379
    Prev
    Next
    INDEX
    Explanations

    instances of the word "down" and related terms or contexts in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Viki
    -0.90
     Magi
    -0.87
    Ivoire
    -0.80
    érêt
    -0.77
     geschenk
    -0.73
     belangrij
    -0.73
    NewUrlParser
    -0.71
     Chel
    -0.70
    getImage
    -0.69
     музы
    -0.69
    POSITIVE LOGITS
     down
    2.47
     Down
    2.30
    Down
    2.24
     DOWN
    2.19
    down
    2.11
    DOWN
    1.98
    downs
    1.82
     downs
    1.71
    Downs
    1.67
     Downs
    1.55
    Activations Density 0.070%

    No Known Activations