© 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. 15444
    Prev
    Next
    INDEX
    Explanations

    academic or scientific terms related to various fields of study

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

    Scientific or academic journal references

    np_acts-logits-general · gemini-2.0-flash

    journal titles

    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
     समीक्षक
    -0.62
     &___
    -0.59
    }{*}{}
    -0.50
    Parcelize
    -0.49
     joined
    -0.49
    новништво
    -0.47
    ADORA
    -0.46
    vastava
    -0.44
    ikor
    -0.44
     ettei
    -0.44
    POSITIVE LOGITS
    клопе
    0.74
     jl
    0.70
    PreInfinity
    0.65
     JJ
    0.63
     jd
    0.60
    jsonwebtoken
    0.59
     jc
    0.59
    JJ
    0.57
     jj
    0.55
     estimés
    0.55
    Activations Density 0.334%

    No Known Activations