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. 25-GEMMASCOPE-RES-16K
    6. 5930
    Prev
    Next
    INDEX
    Explanations

    references to academic citations and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeConstraints
    -0.65
    <?
    -0.61
    imageshack
    -0.61
     Portail
    -0.56
    dataclass
    -0.56
    
    -0.54
     newName
    -0.52
    ulemon
    -0.52
    υμα
    -0.51
    بوابة
    -0.50
    POSITIVE LOGITS
     ed
    1.02
    Eds
    0.99
    Ed
    0.98
    ed
    0.95
    eds
    0.93
     Ed
    0.93
     Eds
    0.93
     editor
    0.92
     eds
    0.90
     editors
    0.88
    Activations Density 0.166%

    No Known Activations