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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5825
    Prev
    Next
    INDEX
    Explanations

    informal expressions of humor and conversational tone

    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
    GEBURTSDATUM
    -0.73
     Taktlose
    -0.63
     يتيمه
    -0.59
    ConstraintMaker
    -0.59
     المعيارى
    -0.59
    TypedDataSet
    -0.54
    readystatechange
    -0.53
    tvguidetime
    -0.53
    sidemargin
    -0.52
    OrNil
    -0.50
    POSITIVE LOGITS
     frequently
    1.45
     alot
    1.37
     paljon
    1.28
     extensively
    1.26
     regularly
    1.16
     beaucoup
    1.15
     lots
    1.15
    frequently
    1.13
     much
    1.10
     often
    1.08
    Activations Density 0.508%

    No Known Activations