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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5485
    Prev
    Next
    INDEX
    Explanations

    concepts related to digital advertising strategies and brand storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    brand image and representation

    np_acts-logits-general · gemini-2.0-flash

    brand storytelling and image

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <>",
    -0.66
    HideFlags
    -0.57
    ItemLayout
    -0.56
    ineno
    -0.55
    tanleria
    -0.55
    urnum
    -0.54
    Према
    -0.53
     Adjustment
    -0.52
    SizeMode
    -0.52
    UnifiedTopology
    -0.51
    POSITIVE LOGITS
     brand
    0.86
     branding
    0.82
     branded
    0.74
     Branding
    0.73
    Brand
    0.69
    brand
    0.68
    BRAND
    0.68
     brands
    0.67
     BRAND
    0.66
     compelling
    0.65
    Activations Density 0.225%

    No Known Activations