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. 15195
    Prev
    Next
    INDEX
    Explanations

    instances of the word "once."

    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
    Kami
    -0.54
    変わり
    -0.54
     meda
    -0.52
    ći
    -0.52
    quées
    -0.51
    AH
    -0.51
    relevant
    -0.50
     übere
    -0.50
    craft
    -0.50
     Geno
    -0.50
    POSITIVE LOGITS
     once
    3.68
    once
    3.35
     ONCE
    3.10
    Once
    3.08
     Once
    3.07
    ONCE
    2.81
     einmal
    1.77
    一度
    1.53
     مرة
    1.51
     egyszer
    1.51
    Activations Density 0.036%

    No Known Activations