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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-GEMMASCOPE-RES-16K
    6. 9490
    Prev
    Next
    INDEX
    Explanations

    the concept of principles or foundational ideas 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 @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ediciones
    -0.76
    hoebe
    -0.71
     berea
    -0.67
    eye
    -0.65
     Guarda
    -0.64
    дарь
    -0.64
     Arag
    -0.63
    aget
    -0.63
    tilde
    -0.62
    flare
    -0.62
    POSITIVE LOGITS
     principles
    1.60
     Principles
    1.57
    Principles
    1.51
     Principle
    1.51
     principle
    1.49
     PRINCIPLES
    1.47
     PRINCIP
    1.38
    principles
    1.37
    principle
    1.34
    Principle
    1.34
    Activations Density 0.057%

    No Known Activations