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-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 8440
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or symbols related to prime numbers or derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.60
    extAlignment
    -0.53
     tetto
    -0.53
    Plateau
    -0.53
     Labyrinth
    -0.52
     MATHEMATICAL
    -0.51
     CALCUL
    -0.51
    arschu
    -0.51
     SOCIETY
    -0.51
     INTERPRET
    -0.50
    POSITIVE LOGITS
    prime
    0.95
     prime
    0.63
    ′
    0.54
    Prime
    0.52
    PRIME
    0.49
     Prime
    0.49
    ′-
    0.48
     ’
    0.47
    ′,
    0.45
     primes
    0.45
    Activations Density 0.670%

    No Known Activations