© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 4934
    Prev
    Next
    INDEX
    Explanations

    the word "fully" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sob
    -0.65
     remembered
    -0.53
    åg
    -0.53
     schia
    -0.52
     Verteilung
    -0.51
     ولد
    -0.50
     Tast
    -0.49
     fortunes
    -0.49
    kkue
    -0.48
     chaud
    -0.48
    POSITIVE LOGITS
     fully
    4.23
     Fully
    3.95
    Fully
    3.83
    fully
    2.90
    FULLY
    2.83
     completely
    2.40
     Completely
    2.32
     pleinement
    2.29
     sepenuhnya
    2.27
     полностью
    2.23
    Activations Density 0.106%

    No Known Activations