© 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 EvalsExportsAPI 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. 5839
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to YAML and configurations

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

    Follows first-person pronouns or subjective pronouns

    np_acts-logits-general · gemini-2.0-flash

    I think

    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
    ImageContext
    -0.59
     fucking
    -0.57
    fucking
    -0.51
     fuckin
    -0.51
     Fucking
    -0.45
     fuck
    -0.45
    nodoc
    -0.45
    stupid
    -0.44
    Хьажоргаш
    -0.44
     stupid
    -0.44
    POSITIVE LOGITS
    Kindly
    0.52
     Putih
    0.46
    rungsseite
    0.46
     Bapak
    0.46
     unfortunately
    0.44
     Kindly
    0.43
     souhaitez
    0.43
    verifyException
    0.43
     collega
    0.42
     colleague
    0.41
    Activations Density 0.301%

    No Known Activations