© 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. 35-GEMMASCOPE-RES-16K
    11. 12454
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the significance and seriousness of various subjects and requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.51
     estekak
    -0.50
     CascadeType
    -0.47
    delwed
    -0.45
     Chwiliwch
    -0.44
    RTEE
    -0.44
    MarshalTo
    -0.43
    SharedCtor
    -0.43
    MethodManager
    -0.43
     defaultstate
    -0.42
    POSITIVE LOGITS
     serious
    3.38
    serious
    3.13
    Serious
    3.02
     Serious
    3.02
     seriousness
    2.88
     seriously
    2.73
     serius
    2.69
     serio
    2.39
    seriously
    2.38
     sérieux
    2.33
    Activations Density 0.411%

    No Known Activations