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. 21-GEMMASCOPE-RES-16K
    6. 1059
    Prev
    Next
    INDEX
    Explanations

    terms related to catalysts and chemical reactions, particularly focusing on properties and changes under varying conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lccn
    -0.52
     nakalista
    -0.51
     Италијани
    -0.49
    ьаж
    -0.47
    違います
    -0.47
    তথ্যসূত্র
    -0.47
    witter
    -0.46
    OrBuilder
    -0.46
     unbedingt
    -0.46
    曖昧さ回避
    -0.45
    POSITIVE LOGITS
     resulting
    2.06
     thereby
    1.96
    resulting
    1.91
     allowing
    1.79
     thus
    1.76
     causing
    1.70
     enabling
    1.67
     giving
    1.62
     waardoor
    1.61
     making
    1.60
    Activations Density 1.643%

    No Known Activations