Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2761
    Prev
    Next
    INDEX
    Explanations

    references to political dynamics and relationships

    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
     myſelf
    -0.89
     itſelf
    -0.74
    новништво
    -0.74
     himſelf
    -0.73
     fhew
    -0.73
     leaſt
    -0.73
    parsedMessage
    -0.72
     uſed
    -0.72
     muſt
    -0.72
     raiſ
    -0.70
    POSITIVE LOGITS
     nhờ
    0.59
    AxisAlignment
    0.54
     grâce
    0.53
     relying
    0.52
    marle
    0.52
     using
    0.51
     because
    0.50
     dựa
    0.48
     gracias
    0.48
     due
    0.48
    Activations Density 0.767%

    No Known Activations