© 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. 23-GEMMASCOPE-RES-16K
    6. 8619
    Prev
    Next
    INDEX
    Explanations

    phrases expressing utility and helpfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.59
    ViewInit
    -0.54
    xrTableCell
    -0.54
     internetowa
    -0.52
    Predecesor
    -0.51
    kegaard
    -0.50
     ObjectParameter
    -0.50
    WebVitals
    -0.49
    ChromeDriver
    -0.46
    bitat
    -0.46
    POSITIVE LOGITS
     useful
    1.10
    useful
    0.93
     helpful
    0.93
    Useful
    0.86
     Useful
    0.84
     usefulness
    0.82
     berguna
    0.81
     útil
    0.76
    helpful
    0.73
     úteis
    0.70
    Activations Density 0.339%

    No Known Activations