© 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. 3814
    Prev
    Next
    INDEX
    Explanations

    statements about capability and potential outcomes in various contexts

    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
    ThroughAttribute
    -0.70
     ModelExpression
    -0.62
     Taktlose
    -0.59
    Демографія
    -0.58
    انيف
    -0.57
     Waray
    -0.53
    новниш
    -0.53
    zyła
    -0.53
     sovere
    -0.51
    Життєпис
    -0.51
    POSITIVE LOGITS
     fácilmente
    1.07
     easily
    0.99
     facilmente
    0.95
     facilement
    0.91
     safely
    0.86
    easily
    0.83
     conceivably
    0.72
    ได้
    0.71
     Easily
    0.71
    媲
    0.69
    Activations Density 1.373%

    No Known Activations