© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8814
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty and attempts to regain control in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     perfecting
    -0.41
    SharedCtor
    -0.40
    jspb
    -0.39
    typeDefinition
    -0.38
    )++;
    -0.37
    ercises
    -0.36
    FontOfSize
    -0.36
    ghest
    -0.35
     soddis
    -0.35
     Krzyż
    -0.35
    POSITIVE LOGITS
     revive
    0.99
     revived
    0.96
     regained
    0.91
     rebound
    0.90
     regain
    0.89
     bounce
    0.89
     revival
    0.86
     resurrect
    0.85
     bounced
    0.85
     bouncing
    0.84
    Activations Density 0.450%

    No Known Activations