© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5005
    Prev
    Next
    INDEX
    Explanations

    terms related to weakness or mildness in various contexts

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

    adjectives describing something as limited, minimal, or low in intensity or degree.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ColumnHeaders
    -0.42
    sendRedirect
    -0.40
     unab
    -0.38
    馳走
    -0.37
     entrenched
    -0.36
    secuencias
    -0.36
     squarely
    -0.35
    ungsver
    -0.35
     Beur
    -0.35
     Mackay
    -0.35
    POSITIVE LOGITS
     (<
    0.72
    ながらも
    0.57
    ながら
    0.57
     تضيفلها
    0.54
    🤏
    0.52
     ながら
    0.51
     ביותר
    0.50
    AndEndTag
    0.49
     gehalten
    0.47
    BagConstraints
    0.47
    Activations Density 0.508%

    No Known Activations