© 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. 11887
    Prev
    Next
    INDEX
    Explanations

    various forms and types of ice-related products or references

    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
    affaire
    -0.32
     humanidade
    -0.31
     bestuur
    -0.31
    ornment
    -0.31
     сына
    -0.30
     suami
    -0.30
    getResultList
    -0.30
     Ejecutivo
    -0.30
     questione
    -0.29
    endorong
    -0.29
    POSITIVE LOGITS
     ice
    1.22
     Ice
    1.13
    Ice
    1.08
     ICE
    1.02
     Eis
    0.86
    氷
    0.84
     skating
    0.83
    Eis
    0.81
     iceberg
    0.81
    ice
    0.81
    Activations Density 0.074%

    No Known Activations