© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 11398
    Prev
    Next
    INDEX
    Explanations

    typical phrases and structure commonly used in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.37
    Distribuzione
    -0.33
     Withdrawal
    -0.32
     bodem
    -0.32
     strane
    -0.32
     VIAF
    -0.31
    bucha
    -0.31
    Soorten
    -0.30
    URLEncoder
    -0.30
    страция
    -0.30
    POSITIVE LOGITS
     usual
    0.75
    usual
    0.69
    相変わらず
    0.64
    FlatAppearance
    0.63
     Usual
    0.62
    Usual
    0.62
    今回も
    0.61
    adaptiveStyles
    0.59
     typical
    0.57
     pinulongan
    0.56
    Activations Density 0.235%

    No Known Activations