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. 10-GEMMASCOPE-RES-16K
    6. 5478
    Prev
    Next
    INDEX
    Explanations

    concepts related to targeted advertising strategies and audience segmentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ineno
    -0.80
     intptr
    -0.79
    verwijspagina
    -0.77
     msglen
    -0.74
     pinulongan
    -0.73
    AndEndTag
    -0.72
     مرئيه
    -0.72
    ⓧ
    -0.70
    Geplaatst
    -0.70
    شهاد
    -0.69
    POSITIVE LOGITS
     clientèle
    0.89
     customers
    0.80
     demographic
    0.71
     demographics
    0.64
     Demographic
    0.63
    customers
    0.62
     customer
    0.60
     Customers
    0.60
     clients
    0.60
    Demographic
    0.59
    Activations Density 0.270%

    No Known Activations