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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 8391
    Prev
    Next
    INDEX
    Explanations

    terms related to "pop" and "population."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.73
    Vidite
    -0.68
    PerformLayout
    -0.63
    cshtml
    -0.57
     disambiguazione
    -0.56
     iNdEx
    -0.56
     Réponses
    -0.55
     חיצוניים
    -0.54
     ostavi
    -0.54
     banc
    -0.54
    POSITIVE LOGITS
     pop
    1.09
     Pop
    1.04
     POP
    1.01
    Pop
    0.99
    pop
    0.93
    POP
    0.93
     pops
    0.92
     culture
    0.83
    pops
    0.81
    ulating
    0.78
    Activations Density 0.081%

    No Known Activations