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. 20-GEMMASCOPE-RES-16K
    6. 770
    Prev
    Next
    INDEX
    Explanations

    phrases and names associated with collaboration and joint efforts among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -1.24
     himself
    -0.94
    himself
    -0.92
    adaptiveStyles
    -0.86
    SequentialGroup
    -0.84
     sám
    -0.82
     للاسماء
    -0.81
    GEBURTSDATUM
    -0.81
     distanciation
    -0.75
    IndentedString
    -0.75
    POSITIVE LOGITS
     their
    1.28
    Their
    1.26
     Their
    1.19
    their
    1.17
     respectively
    1.14
     themselves
    1.10
     eds
    1.03
     THEIR
    0.91
    他们的
    0.90
    他們的
    0.88
    Activations Density 0.288%

    No Known Activations