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. 2353
    Prev
    Next
    INDEX
    Explanations

    scientific concepts and terms related to advancements in drug metabolism and biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    combination or association

    np_acts-logits-general · gemini-2.0-flash

    combined or coupled

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    vible
    -0.59
    లాలు
    -0.53
     revanche
    -0.51
    
    -0.51
    曖昧さ回避
    -0.50
    Specifiche
    -0.50
    pshots
    -0.49
    ولوج
    -0.49
    脚注の使い方
    -0.48
     يكن
    -0.48
    POSITIVE LOGITS
     combined
    2.59
     coupled
    2.52
    combined
    2.21
     paired
    2.16
     Combined
    2.10
     Coupled
    2.08
     accompanied
    2.02
    Combined
    1.98
     combinado
    1.97
    coupled
    1.94
    Activations Density 1.209%

    No Known Activations