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. 2-GEMMASCOPE-RES-16K
    6. 6645
    Prev
    Next
    INDEX
    Explanations

    instances of the word "roll."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prieto
    -0.74
    httphttps
    -0.57
    LayoutConstraint
    -0.56
     Solana
    -0.56
     πως
    -0.56
     Mejía
    -0.56
    )++;
    -0.55
     δὲ
    -0.54
     bı
    -0.53
     Nacionales
    -0.53
    POSITIVE LOGITS
     roll
    4.35
     Roll
    3.96
     rolls
    3.81
    Roll
    3.80
    roll
    3.80
     ROLL
    3.73
     rolled
    3.42
    ROLL
    3.32
     rolling
    3.22
    rolls
    3.05
    Activations Density 0.049%

    No Known Activations