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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 7345
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "nature" and its various characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colloidal
    -0.74
    ؤلاء
    -0.71
     valido
    -0.71
    λαι
    -0.70
     akong
    -0.69
     SqlCommand
    -0.67
    تفصیلات
    -0.67
     Escolar
    -0.67
     wrongful
    -0.66
     carreaux
    -0.65
    POSITIVE LOGITS
     nature
    2.36
     Nature
    2.27
     NATURE
    2.21
    Nature
    2.08
    nature
    1.97
    NATURE
    1.92
     natures
    1.75
     natureza
    1.60
     naturaleza
    1.44
     natura
    1.35
    Activations Density 0.052%

    No Known Activations