© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9866
    Prev
    Next
    INDEX
    Explanations

    references to populations and population-related concepts

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

    "population"

    np_acts-logits-general · gemini-2.0-flash

    population genetics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.47
     Prüf
    -0.44
     André
    -0.43
    داية
    -0.42
    André
    -0.42
     dritte
    -0.40
    experiments
    -0.40
    Conseils
    -0.40
     experiment
    -0.40
     dream
    -0.39
    POSITIVE LOGITS
     population
    2.33
     Population
    2.13
    Population
    2.06
    population
    2.06
     populations
    1.91
     POPULATION
    1.88
     Populations
    1.70
     população
    1.57
    populations
    1.55
     población
    1.53
    Activations Density 0.210%

    No Known Activations