© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5725
    Prev
    Next
    INDEX
    Explanations

    terms related to "pop" and its variations, particularly in context to culture or population

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Pop" followed by certain words

    np_acts-logits-general · gemini-2.0-flash

    Pop followed by common words/phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    -0.82
    Vidite
    -0.70
    migrationBuilder
    -0.67
     autorytatywna
    -0.66
    PerformLayout
    -0.66
     Réponses
    -0.64
     iNdEx
    -0.64
     disambiguazione
    -0.63
    ValueStyle
    -0.62
    ########.
    -0.62
    POSITIVE LOGITS
     pop
    1.15
     Pop
    1.06
     POP
    1.03
    Pop
    1.01
    pop
    0.98
    POP
    0.94
     pops
    0.88
     culture
    0.83
     popping
    0.75
     Pops
    0.74
    Activations Density 0.051%

    No Known Activations