© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1497
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to statistics or data analysis

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

    references to medical conditions or treatments

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

    calls itself

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     themſelves
    -1.02
     Савезне
    -1.00
     myſelf
    -0.99
     himſelf
    -0.95
     pleaſure
    -0.95
     bezeichneter
    -0.94
     ſever
    -0.93
    ########.
    -0.92
     deſt
    -0.92
     Jefus
    -0.90
    POSITIVE LOGITS
    <bos>
    0.63
     ollut
    0.51
     aikaa
    0.50
     ditutup
    0.46
     voltak
    0.45
     tehdä
    0.44
    ydı
    0.43
     lijn
    0.42
    rdı
    0.42
     gehabt
    0.41
    Activations Density 0.046%

    No Known Activations