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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6968
    Prev
    Next
    INDEX
    Explanations

    terms related to vehicle safety systems and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    abstractmethod
    -0.67
    ScopeManager
    -0.62
    存于互联网档案馆
    -0.59
     subprocess
    -0.59
    springer
    -0.57
     jScrollPane
    -0.57
    GeneratedCode
    -0.56
     rodríguez
    -0.56
     endwhile
    -0.55
    󠁿
    -0.55
    POSITIVE LOGITS
    ui
    0.68
    ain
    0.60
    ail
    0.60
    ai
    0.59
    AIN
    0.57
     Lait
    0.57
     Aik
    0.54
     Iain
    0.53
    iai
    0.52
    Aid
    0.52
    Activations Density 0.830%

    No Known Activations