© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7982
    Prev
    Next
    INDEX
    Explanations

    instances of the word "volume" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    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
    -0.73
     dAtA
    -0.71
     تانيه
    -0.67
     Hadd
    -0.63
     Hopf
    -0.60
     Barclay
    -0.60
     tensile
    -0.60
     Questa
    -0.59
     biliary
    -0.58
    tır
    -0.58
    POSITIVE LOGITS
     volume
    3.44
    volume
    3.12
     Volume
    3.11
     volumes
    3.06
    Volume
    2.98
     VOLUME
    2.85
     Volumes
    2.68
    volumes
    2.63
     volumen
    2.61
    VOLUME
    2.60
    Activations Density 0.058%

    No Known Activations