© 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. 15-GEMMASCOPE-RES-16K
    6. 2597
    Prev
    Next
    INDEX
    Explanations

    references to educational materials and their authors

    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
    apimachinery
    -0.49
     hObject
    -0.46
    matchCondition
    -0.45
    codehaus
    -0.44
    httphttps
    -0.43
    ---*/
    -0.42
    チコミ
    -0.42
    PRNewswire
    -0.42
    LikeLiked
    -0.41
     Photographie
    -0.41
    POSITIVE LOGITS
     teaching
    1.14
     textbooks
    1.01
     instructional
    0.99
     pedagogical
    0.97
    teaching
    0.95
     textbook
    0.94
     pedagogy
    0.92
     Teaching
    0.91
     didac
    0.90
     educational
    0.89
    Activations Density 0.415%

    No Known Activations