© 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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8619
    Prev
    Next
    INDEX
    Explanations

    the term "superior" indicating a comparison of quality or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jäger
    -0.36
    az
    -0.33
    ic
    -0.32
    сти
    -0.31
     Skinner
    -0.31
    """.
    -0.30
     produced
    -0.30
     industry
    -0.30
     producing
    -0.29
    or
    -0.29
    POSITIVE LOGITS
    superior
    0.79
    tagHelperRunner
    0.78
    ThroughAttribute
    0.77
    PerformLayout
    0.75
     queſta
    0.75
     تضيفلها
    0.74
    windowFixed
    0.73
     NSCoder
    0.70
    󠁮
    0.69
    SequentialGroup
    0.69
    Activations Density 0.356%

    No Known Activations