© 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. 25-GEMMASCOPE-RES-16K
    6. 6581
    Prev
    Next
    INDEX
    Explanations

    questions and phrases that start with "Are" and relate to inquiries about the presence or condition of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MergeFrom
    -0.62
    
    -0.60
    versy
    -0.58
     it
    -0.57
     quanto
    -0.55
     verksamhet
    -0.54
     őket
    -0.53
     aikaa
    -0.52
    pography
    -0.52
     that
    -0.51
    POSITIVE LOGITS
     they
    0.94
     we
    0.83
     these
    0.73
    llano
    0.67
     THEY
    0.66
     они
    0.65
     οι
    0.64
     wir
    0.64
     those
    0.64
     wij
    0.63
    Activations Density 0.106%

    No Known Activations