© 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. 40-GEMMASCOPE-RES-16K
    11. 5807
    Prev
    Next
    INDEX
    Explanations

    sentiments of frustration and futility regarding societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     always
    -0.69
     alſo
    -0.66
     also
    -0.63
    always
    -0.62
     alfo
    -0.60
     tiež
    -0.55
    Always
    -0.54
    already
    -0.52
     already
    -0.52
     també
    -0.51
    POSITIVE LOGITS
     ever
    1.25
     bothered
    1.18
     bother
    1.14
     siquiera
    1.13
     EVER
    1.13
     bothering
    1.06
     even
    1.02
     bothers
    0.98
     jemals
    0.90
    even
    0.89
    Activations Density 0.753%

    No Known Activations