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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 68
    Prev
    Next
    INDEX
    Explanations

    references to numerical data formatting and calculations

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

    Numbers converted to different units

    np_acts-logits-general · gemini-2.0-flash

    decimal numbers and units

    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
    ContentAsync
    -0.65
    \|^{
    -0.50
     henvisninger
    -0.50
    PullParser
    -0.48
     saites
    -0.46
    Tikang
    -0.46
    GIVEREF
    -0.46
     Feder
    -0.46
    })();
    
    -0.44
    ]^{
    -0.43
    POSITIVE LOGITS
     decimal
    0.98
     digits
    0.97
     zeros
    0.97
     zeroes
    0.93
     digit
    0.90
     numerals
    0.78
     numeric
    0.76
    decimal
    0.76
     decimals
    0.76
     numeral
    0.75
    Activations Density 0.547%

    No Known Activations