© 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. 20-GEMMASCOPE-RES-16K
    11. 11986
    Prev
    Next
    INDEX
    Explanations

    references to sources and reporting in news

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

    information attribution

    np_acts-logits-general · gemini-2.0-flash

    information sources and their claims

    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
    +#+#
    -0.66
    AddTagHelper
    -0.63
     ویکی‌پدی
    -0.58
    findpost
    -0.54
    OrNil
    -0.51
    RTGC
    -0.50
     الوطنيه
    -0.49
    
    -0.49
    Tembelea
    -0.48
     فريبيس
    -0.48
    POSITIVE LOGITS
     sources
    1.10
    Sources
    1.00
     Sources
    0.92
     interviewed
    0.91
     insiders
    0.89
     familiar
    0.87
    Fontes
    0.84
     source
    0.83
    sources
    0.82
     interviewees
    0.79
    Activations Density 0.159%

    No Known Activations