© 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. 28-GEMMASCOPE-RES-16K
    11. 11618
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or processes involving comments and commands

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

    repetition or renewal

    np_acts-logits-general · gemini-2.0-flash

    doing again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gsSP
    -0.35
     bricks
    -0.34
    roek
    -0.34
    städ
    -0.33
    matt
    -0.32
     MATT
    -0.32
     matur
    -0.32
    Rüyada
    -0.32
     volunt
    -0.31
    lequin
    -0.31
    POSITIVE LOGITS
     again
    1.79
    again
    1.61
    Again
    1.55
     Again
    1.46
     tekrar
    1.38
     novamente
    1.38
     nuevamente
    1.34
     opnieuw
    1.31
     erneut
    1.29
     AGAIN
    1.27
    Activations Density 0.563%

    No Known Activations