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. 24-GEMMASCOPE-RES-16K
    6. 13964
    Prev
    Next
    INDEX
    Explanations

    terms related to evolutionary biology and species divergence

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

    Species, populations, or distributions

    np_acts-logits-general · gemini-2.0-flash

    invasive species populations introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ostavi
    -0.80
    ReusableCell
    -0.67
    AnchorStyles
    -0.65
    Autoritní
    -0.62
     surla
    -0.62
     useStyles
    -0.61
     esternos
    -0.61
    ytet
    -0.59
    empuan
    -0.59
    itemBuilder
    -0.59
    POSITIVE LOGITS
     populations
    1.04
     introductions
    0.95
     introduced
    0.88
     introduction
    0.86
     population
    0.84
     invasive
    0.81
     introdu
    0.81
    populations
    0.80
    Populations
    0.76
     Populations
    0.76
    Activations Density 0.694%

    No Known Activations