© 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. 33-GEMMASCOPE-RES-16K
    11. 3133
    Prev
    Next
    INDEX
    Explanations

    information related to insurance policies and coverage options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.61
     aparentemente
    -0.47
     PeEnEo
    -0.47
     Waray
    -0.47
     hitherto
    -0.45
    bootstrapcdn
    -0.42
     jusque
    -0.38
     ontem
    -0.38
    Legături
    -0.38
    esercito
    -0.38
    POSITIVE LOGITS
     remember
    1.13
     Remember
    1.05
    Remember
    1.03
    remember
    0.88
     ensure
    0.87
    Ensure
    0.85
     Ensure
    0.84
    Keep
    0.84
     pastikan
    0.83
    Always
    0.82
    Activations Density 0.347%

    No Known Activations