© 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. 13754
    Prev
    Next
    INDEX
    Explanations

    references to sides or positioning in a variety of contexts, likely indicated by the word "side"

    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
    новниш
    -0.81
    jillo
    -0.80
     Erfurt
    -0.80
    Бахар
    -0.80
     disponibilités
    -0.78
    SerializeField
    -0.77
     poveznice
    -0.76
    ']);
    -0.76
     
    -0.76
     للمعارف
    -0.74
    POSITIVE LOGITS
     side
    2.35
     Side
    2.30
     SIDE
    2.27
    Side
    2.21
     sides
    2.17
    side
    2.04
    SIDE
    1.99
     Sides
    1.99
    Sides
    1.67
    sides
    1.65
    Activations Density 0.064%

    No Known Activations