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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 7603
    Prev
    Next
    INDEX
    Explanations

    references to silver and its compounds in various contexts

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

    Silver and csv files

    np_acts-logits-general · gemini-2.0-flash

    silver compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    defn
    -0.75
     aDecoder
    -0.75
    ----</
    -0.69
    الإنجليزية
    -0.68
    protoimpl
    -0.68
    er
    -0.68
     Martel
    -0.65
     Hukum
    -0.63
    AnchorStyles
    -0.62
    stoffe
    -0.62
    POSITIVE LOGITS
     Whittier
    0.81
    argento
    0.78
     Klee
    0.78
     Pickett
    0.77
     Kitz
    0.76
     weddings
    0.76
     Wah
    0.75
     برابوك
    0.74
     bismuth
    0.73
     Balt
    0.72
    Activations Density 0.464%

    No Known Activations