© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7965
    Prev
    Next
    INDEX
    Explanations

    mentions of successful outcomes or resolutions in a context of challenges or issues

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

    Preceding verbs (helps, thanks, has)

    np_acts-logits-general · gemini-2.0-flash

    enabled, implemented, developed

    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
     IMHO
    -0.61
    !!!”
    -0.60
    !!!"
    -0.59
     our
    -0.59
     myſelf
    -0.58
     hereof
    -0.57
     okuyayım
    -0.57
    !!!!
    -0.56
     meines
    -0.56
     denna
    -0.55
    POSITIVE LOGITS
     pihaknya
    0.97
     lantaran
    0.55
     dirinya
    0.52
     müsse
    0.50
     “
    0.47
     könne
    0.46
    ，「
    0.45
    ：“
    0.43
    ：「
    0.40
     he
    0.39
    Activations Density 0.430%

    No Known Activations