© 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. 1-GEMMASCOPE-RES-16K
    11. 6665
    Prev
    Next
    INDEX
    Explanations

    the name "Jane" and various occurrences of the word "shine" in relation to destinations

    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
    middels
    -0.80
    Hochspringen
    -0.77
     AssemblyCompany
    -0.74
    LookAnd
    -0.72
     noDo
    -0.71
    InputBorder
    -0.70
     BorderSide
    -0.70
     snippetHide
    -0.70
    ureusement
    -0.66
    %"),
    -0.66
    POSITIVE LOGITS
     Jane
    0.98
    Jane
    0.97
     shine
    0.96
    ug
    0.87
     JANE
    0.75
     shines
    0.73
    ación
    0.68
     Shine
    0.66
     Tur
    0.65
     shone
    0.64
    Activations Density 0.055%

    No Known Activations