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. 16-GEMMASCOPE-RES-16K
    6. 9071
    Prev
    Next
    INDEX
    Explanations

    elements of personal and family life, focusing on activities enjoyed with loved ones

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

    Hobbies and activities

    np_acts-logits-general · gemini-2.0-flash

    enjoying hobbies and leisure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Referencie
    -0.57
     vérit
    -0.57
    bigsqcup
    -0.55
     linguistique
    -0.55
     grève
    -0.54
     françaises
    -0.53
     rangs
    -0.53
     conséquences
    -0.52
    rån
    -0.52
     fermée
    -0.51
    POSITIVE LOGITS
     dab
    0.66
     hobby
    0.63
     enjoys
    0.61
     golf
    0.60
     hobbies
    0.60
     tinkering
    0.59
     hiking
    0.59
     avid
    0.59
     Avid
    0.59
     gardening
    0.58
    Activations Density 0.118%

    No Known Activations