© 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. 9557
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial health and wellbeing

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

    after prepositions (, . about when)

    np_acts-logits-general · gemini-2.0-flash

    people all about how to get ahead

    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
     failed
    -0.52
     unsuitable
    -0.48
    になってしまう
    -0.48
     fails
    -0.47
    どうしても
    -0.46
     leider
    -0.45
     ineffec
    -0.45
     придется
    -0.45
     inadequate
    -0.45
     failing
    -0.45
    POSITIVE LOGITS
     confidently
    0.75
     flourishing
    0.75
    improved
    0.72
     improved
    0.72
    confident
    0.69
     excellently
    0.68
     strengthened
    0.66
     prosper
    0.66
     confident
    0.66
     excellent
    0.66
    Activations Density 0.479%

    No Known Activations