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. 15-GEMMASCOPE-RES-16K
    6. 1607
    Prev
    Next
    INDEX
    Explanations

    keywords related to film production and shooting locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.57
     TOPOLOGY
    -0.54
    ças
    -0.54
    ритори
    -0.52
    ifrance
    -0.51
     aanbod
    -0.51
    KeySpec
    -0.49
     divisors
    -0.48
    Resumo
    -0.48
     Leibniz
    -0.48
    POSITIVE LOGITS
     filmed
    1.03
     filming
    0.97
     recording
    0.95
     recorded
    0.92
     photographed
    0.91
     shoot
    0.83
     photographing
    0.83
     photoshoot
    0.83
     footage
    0.81
    Filming
    0.81
    Activations Density 0.354%

    No Known Activations