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. 16-GEMMASCOPE-RES-16K
    6. 8344
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to genetic mutations and assays

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

    Code-related text snippets

    np_acts-logits-general · gemini-2.0-flash

    code keywords followed by identifiers

    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
    цездатний
    -0.84
    FieldBuilder
    -0.83
     zaragoza
    -0.80
    webElementXpaths
    -0.80
    SharedDtor
    -0.78
     bekasi
    -0.78
    __':
    
    -0.77
    kháu
    -0.77
     comigo
    -0.76
     AssemblyCulture
    -0.76
    POSITIVE LOGITS
    line
    1.17
    LINE
    0.94
     line
    0.92
    Line
    0.81
     LINE
    0.77
     Line
    0.76
     <<<<<<<<<<<<<<
    0.69
    cline
    0.64
    lines
    0.63
    linie
    0.59
    Activations Density 0.009%

    No Known Activations