© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 6400
    Prev
    Next
    INDEX
    Explanations

    themes related to accusations, claims, and disputes over responsibility and wastefulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.60
    PYX
    -0.55
    ftagPool
    -0.53
     NSCoder
    -0.52
     perpetuity
    -0.51
    CreateMap
    -0.51
     InputDecoration
    -0.51
    setVerticalGroup
    -0.51
     تانيه
    -0.50
    xically
    -0.49
    POSITIVE LOGITS
     zelf
    0.57
     self
    0.56
    はじめに
    0.54
     vol
    0.51
    self
    0.50
     charbon
    0.49
     agradec
    0.46
     Self
    0.46
    自分で
    0.45
    自助
    0.45
    Activations Density 0.504%

    No Known Activations