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. 17-GEMMASCOPE-RES-16K
    6. 13341
    Prev
    Next
    INDEX
    Explanations

    references to customer engagement and targeting strategies in marketing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onAttach
    -0.51
    Host
    -0.46
     ihop
    -0.45
    Filmografia
    -0.45
     Ανακτήθηκε
    -0.45
    المناصب
    -0.45
    kon
    -0.44
    COLS
    -0.44
    mach
    -0.43
    suri
    -0.43
    POSITIVE LOGITS
     buying
    1.00
     purchasing
    0.93
    buying
    0.93
    Buying
    0.90
     Buying
    0.87
     purchase
    0.80
     Purchasing
    0.80
    buyers
    0.79
     consumers
    0.77
     membeli
    0.76
    Activations Density 0.382%

    No Known Activations