© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38507
    Prev
    Next
    INDEX
    Explanations

    titles of books, songs, or other creative works, particularly those with a collaborative or thematic focus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -1.00
     <<<<<<<<<<<<<<
    -0.95
     resourceCulture
    -0.88
    InjectAttribute
    -0.83
    expandindo
    -0.82
    SourceChecksum
    -0.82
    Hentet
    -0.81
     للاسماء
    -0.80
    
    -0.78
    الحياه
    -0.78
    POSITIVE LOGITS
     ")[
    0.50
    iato
    0.47
    ...",
    0.47
     #
    0.46
    iseta
    0.45
     kinda
    0.44
    "].
    0.44
     quote
    0.43
     ')[
    0.43
     motto
    0.43
    Activations Density 0.016%

    No Known Activations