Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1945
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement and quantities of volume

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.68
     defaultstate
    -0.61
    Twas
    -0.57
    +#+
    -0.57
     BoxFit
    -0.57
     Jara
    -0.56
     siquiera
    -0.56
    OrNil
    -0.56
     alcuna
    -0.52
    niños
    -0.50
    POSITIVE LOGITS
     volumes
    0.92
     Volumes
    0.89
    volumes
    0.82
     VOL
    0.81
     Volume
    0.78
     VOLUME
    0.78
     Volumen
    0.76
    Volumes
    0.75
     vol
    0.75
     Vols
    0.74
    Activations Density 0.087%

    No Known Activations