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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14785
    Prev
    Next
    INDEX
    Explanations

    terms related to population genetics and evolutionary biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.57
     myſelf
    -0.56
     المعيارى
    -0.53
     Monfieur
    -0.53
     himſelf
    -0.52
    CodeDom
    -0.48
    pædia
    -0.48
    ſelf
    -0.46
    phylococcus
    -0.44
     spina
    -0.44
    POSITIVE LOGITS
     anthropogenic
    0.77
     seasonally
    0.61
     spatially
    0.60
     vár
    0.59
     regionally
    0.57
     variability
    0.56
    ugia
    0.55
     annually
    0.54
     preferentially
    0.53
     trophic
    0.52
    Activations Density 1.940%

    No Known Activations