Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 10928
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to celebrity gossip and news

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

    Information source attribution

    np_acts-logits-general · gemini-2.0-flash

    telling celebrity news

    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
     estekak
    -0.70
     Signalez
    -0.70
    ArgsConstructor
    -0.68
     الرياضيه
    -0.60
    ornos
    -0.55
    BackStack
    -0.55
     snippetHide
    -0.54
     يتيمه
    -0.53
     Audiodateien
    -0.53
     aufnehmen
    -0.52
    POSITIVE LOGITS
     gossip
    0.77
     TMZ
    0.72
     paparazzi
    0.68
     Hollywood
    0.65
     celeb
    0.64
     Gossip
    0.64
     entertainment
    0.63
     Entertainment
    0.61
     celebrity
    0.61
     gossi
    0.60
    Activations Density 0.175%

    No Known Activations