Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 250
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols used in formal proofs

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

    mathematical notation and equations, particularly involving Greek letters and symbolic mathematical expressions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    msgTypes
    -0.84
    rungsseite
    -0.79
    <unused41>
    -0.78
    <unused16>
    -0.77
    <unused28>
    -0.77
    <unused17>
    -0.77
    <unused42>
    -0.77
    <unused43>
    -0.77
    <pad>
    -0.77
    <unused14>
    -0.77
    POSITIVE LOGITS
     of
    0.46
     itself
    0.32
     above
    0.31
     elsewhere
    0.31
     near
    0.31
    0.31
     before
    0.30
     led
    0.30
     cannot
    0.30
     alone
    0.29
    Activations Density 0.847%

    No Known Activations