© 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. 7954
    Prev
    Next
    INDEX
    Explanations

    phrases related to suspicion and speculation

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

    [Word] that

    np_acts-logits-general · gemini-2.0-flash

    ideas and 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
    szönöm
    -0.58
     članak
    -0.54
    раздо
    -0.53
    ("")]
    
    -0.53
    yntaxException
    -0.51
    >>()
    -0.51
    OGND
    -0.51
     Himo
    -0.50
    seamnă
    -0.49
     Schengen
    -0.49
    POSITIVE LOGITS
     they
    1.55
     there
    1.48
     we
    1.13
     he
    1.05
    there
    1.02
     she
    1.02
    they
    0.93
     они
    0.91
     THERE
    0.88
     it
    0.86
    Activations Density 0.396%

    No Known Activations