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. 1371
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and their results in equations and calculations

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

    Arithmetic calculations and expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and calculations

    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
     Brou
    -0.52
     hermano
    -0.50
     almost
    -0.48
     Sub
    -0.48
    Normdaten
    -0.46
     nearly
    -0.46
    rishnan
    -0.45
    empla
    -0.45
    clairage
    -0.44
     matrix
    -0.44
    POSITIVE LOGITS
    TintMode
    0.80
    ScopeManager
    0.80
     kasarigan
    0.79
     ostavi
    0.76
     ExecuteAsync
    0.76
     Chwiliwch
    0.74
    URLException
    0.73
     mergeFrom
    0.71
    enschappelijke
    0.71
     ten
    0.69
    Activations Density 0.975%

    No Known Activations