© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11134
    Prev
    Next
    INDEX
    Explanations

    references to ongoing activities or current states

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

    followed by "are," "has," or "have"

    np_acts-logits-general · gemini-2.0-flash

    currently spoken or written

    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
     then
    -1.11
     previously
    -1.10
     originally
    -1.05
     initially
    -1.04
    originally
    -0.99
     awalnya
    -0.98
     ранее
    -0.97
    previously
    -0.97
     anfangs
    -0.96
     previous
    -0.94
    POSITIVE LOGITS
    weer
    0.69
    TestingModule
    0.67
    看来
    0.67
    værende
    0.64
    看來
    0.64
    WebVitals
    0.63
    ш
    0.58
    varande
    0.56
    为止
    0.55
    に至
    0.55
    Activations Density 0.320%

    No Known Activations