© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 9183
    Prev
    Next
    INDEX
    Explanations

    terms related to targeting and analyzing multicultural audiences in marketing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.68
     pinulongan
    -0.65
    =="")
    -0.65
    ArgsConstructor
    -0.64
     الرياضيه
    -0.64
    ineno
    -0.63
    ==""){
    -0.62
     arşivlendi
    -0.61
    hoga
    -0.61
     NSCoder
    -0.59
    POSITIVE LOGITS
     targeted
    0.68
     audiences
    0.62
    targeted
    0.61
    ApiModelProperty
    0.60
     demographic
    0.60
     demographics
    0.58
     audience
    0.57
     potential
    0.57
    ceptive
    0.57
     niche
    0.56
    Activations Density 0.379%

    No Known Activations