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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 14643
    Prev
    Next
    INDEX
    Explanations

    phrases discussing principles and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hoebe
    -0.64
    aget
    -0.63
    lotte
    -0.62
    дарь
    -0.61
    AWAY
    -0.61
     Ediciones
    -0.61
    bamos
    -0.60
    tilde
    -0.60
     Weh
    -0.59
    away
    -0.58
    POSITIVE LOGITS
     principles
    2.18
     Principles
    2.07
     principle
    2.06
    Principles
    2.00
    principles
    1.98
     Principle
    1.96
     PRINCIPLES
    1.88
    principle
    1.83
    Principle
    1.81
     PRINCIP
    1.67
    Activations Density 0.058%

    No Known Activations