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. 18-GEMMASCOPE-RES-16K
    6. 1527
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and experimental conditions

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

    Temperatures (degrees Celsius) and times (minutes or milliseconds)

    np_acts-logits-general · gemini-2.0-flash

    degrees, minutes, milliseconds, molar concentrations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )++;
    -0.71
    Hentet
    -0.64
    ₂)
    -0.61
    .[/
    -0.61
     تضيفلها
    -0.59
    ")){
    
    -0.57
    !");
    
    -0.56
    ++
    
    -0.56
    }
    
    
    -0.55
    !")
    
    -0.55
    POSITIVE LOGITS
    AddTagHelper
    0.71
    rrggbb
    0.70
     propOrder
    0.67
     wikipagina
    0.67
     '\\;'
    0.65
     eenige
    0.63
    TagMode
    0.60
     AssemblyCulture
    0.59
    middels
    0.56
     ModelExpression
    0.55
    Activations Density 1.770%

    No Known Activations