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. 15-GEMMASCOPE-RES-16K
    6. 2188
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and their corresponding notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lcccc
    -0.64
    awtextra
    -0.63
     CURIAM
    -0.60
    cheon
    -0.59
    abor
    -0.57
    leicht
    -0.55
     Nicolás
    -0.54
     плот
    -0.54
     Carrick
    -0.53
     Cano
    -0.52
    POSITIVE LOGITS
     SUM
    1.20
    Sum
    1.15
     Sum
    1.12
    sum
    1.07
    SUM
    1.07
     summation
    1.05
     Summers
    1.00
     Summaries
    1.00
    ∑
    0.96
     sums
    0.94
    Activations Density 0.176%

    No Known Activations