© 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. 11656
    Prev
    Next
    INDEX
    Explanations

    references to personal or individualized concepts

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

    section headers or labels for biographical information (particularly "Personal life" sections).

    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
    IntoConstraints
    -0.84
     disambiguazione
    -0.84
    CppMethod
    -0.83
     surla
    -0.75
    出版年
    -0.73
     Signalez
    -0.70
     estekak
    -0.69
    IUrlHelper
    -0.68
    httphttps
    -0.65
    expandindo
    -0.64
    POSITIVE LOGITS
     personal
    0.79
     Personal
    0.76
    Personal
    0.73
    personal
    0.66
     PERSONAL
    0.54
    ersonal
    0.47
    PERSONAL
    0.47
     persönliche
    0.46
     personlig
    0.46
     persoonlijke
    0.42
    Activations Density 0.051%

    No Known Activations