© 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. 40-GEMMASCOPE-RES-16K
    11. 8398
    Prev
    Next
    INDEX
    Explanations

    references to official reports and their consequences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    étoit
    -0.41
    charpe
    -0.38
     ritratto
    -0.36
     strumento
    -0.36
    ynarod
    -0.36
    gypte
    -0.35
     ')
    -0.35
     Grüsse
    -0.35
    SEGUIR
    -0.35
    addPreferred
    -0.34
    POSITIVE LOGITS
    ’
    2.39
    '
    2.14
    ‘
    1.15
    ´
    1.12
    `
    1.01
    \'
    0.99
    ʼ
    0.84
    ′
    0.84
    ＇
    0.83
    ׳
    0.81
    Activations Density 7.628%

    No Known Activations