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. 2732
    Prev
    Next
    INDEX
    Explanations

    terms related to supply and demand dynamics

    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
     Biochim
    -0.91
     Hoh
    -0.79
    וויק
    -0.78
    emang
    -0.76
    Tat
    -0.71
    ‚¬
    -0.71
     Perc
    -0.71
    icke
    -0.71
    ⓧ
    -0.69
    cipar
    -0.68
    POSITIVE LOGITS
     supply
    1.47
     Supply
    1.42
     supplies
    1.40
    Supply
    1.34
    supply
    1.32
     SUPPLY
    1.29
    Supplies
    1.29
     Supplies
    1.28
    supplies
    1.27
    SUPPLY
    1.16
    Activations Density 0.131%

    No Known Activations