© 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. 33-GEMMASCOPE-RES-16K
    11. 186
    Prev
    Next
    INDEX
    Explanations

    references to hair characteristics and comparisons

    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
     Skinner
    -0.35
    STOT
    -0.35
    跨
    -0.34
    endalikan
    -0.34
     Wes
    -0.34
     sail
    -0.33
     REPORTER
    -0.32
     Waray
    -0.32
    HomeAsUpEnabled
    -0.32
     defender
    -0.31
    POSITIVE LOGITS
     hair
    1.30
    Hair
    1.23
     Hair
    1.23
    hair
    1.16
     shampoo
    1.14
    HAIR
    1.08
     scalp
    1.07
     shampo
    1.07
     HAIR
    1.06
     hairstyles
    1.04
    Activations Density 0.070%

    No Known Activations