© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2685
    Prev
    Next
    INDEX
    Explanations

    phrases related to maritime exploration or journeys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BagLayout
    -0.71
    stånd
    -0.58
    offsetof
    -0.51
    Jeografia
    -0.49
     alab
    -0.48
    delige
    -0.47
    ležit
    -0.47
     Distribu
    -0.47
     Anytime
    -0.47
    schen
    -0.46
    POSITIVE LOGITS
    AndEndTag
    0.67
     للاسماء
    0.65
    期刊论文
    0.64
     dàng
    0.62
    apimachinery
    0.62
     parked
    0.61
     owner
    0.60
     Lordships
    0.60
     docked
    0.60
     crew
    0.59
    Activations Density 0.165%

    No Known Activations