© 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. 20-GEMMASCOPE-RES-16K
    6. 8273
    Prev
    Next
    INDEX
    Explanations

    references to specific actions, descriptions, and relationships within a text

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

    lists, descriptions, or references

    np_acts-logits-general · gemini-2.0-flash

    referring to information above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.73
     estekak
    -0.64
    Sucesor
    -0.63
     nedan
    -0.60
     bassist
    -0.57
     lowest
    -0.57
    lowest
    -0.55
     hereinafter
    -0.55
     bottoms
    -0.54
     Decreased
    -0.54
    POSITIVE LOGITS
     above
    1.57
     Above
    1.51
    Above
    1.47
     upper
    1.39
    above
    1.34
     upstairs
    1.34
     aloft
    1.28
     ABOVE
    1.24
     higher
    1.18
    Upper
    1.18
    Activations Density 0.335%

    No Known Activations