© 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. 2-GEMMASCOPE-RES-16K
    11. 1410
    Prev
    Next
    INDEX
    Explanations

    capital letters and specific sequences in text, primarily focusing on letter patterns related to 'A' and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     artificiales
    -0.36
    ordum
    -0.35
     rodillas
    -0.33
    ınır
    -0.33
     implementar
    -0.33
     eşofman
    -0.32
     auttaa
    -0.31
     Dumnezeu
    -0.31
     golpea
    -0.31
     estre
    -0.31
    POSITIVE LOGITS
     sa
    1.41
     Sa
    1.35
     Sá
    1.34
    Sa
    1.34
     SA
    1.33
    SA
    1.30
     Sadie
    1.30
    sa
    1.27
     SAT
    1.24
    SAT
    1.23
    Activations Density 0.576%

    No Known Activations