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. 18-GEMMASCOPE-RES-16K
    6. 807
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic diversity and population genetics

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

    Genetic variation and population structure

    np_acts-logits-general · gemini-2.0-flash

    genetic polymorphism and selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.61
     Reinh
    -0.49
     الرياضيه
    -0.47
     tipped
    -0.45
    hoeddwyd
    -0.44
    صح
    -0.43
    icium
    -0.43
    কা
    -0.43
     pré
    -0.43
     films
    -0.42
    POSITIVE LOGITS
     allele
    0.76
     genetic
    0.75
     SNPs
    0.73
     genotyping
    0.72
    breeding
    0.72
     alleles
    0.69
     haplo
    0.67
    +:+
    0.67
    География
    0.65
     Genetic
    0.65
    Activations Density 1.580%

    No Known Activations