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. 12423
    Prev
    Next
    INDEX
    Explanations

    references to the environment and related environmental concepts

    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
     getLast
    -0.61
     click
    -0.51
    Clik
    -0.49
     getCustomer
    -0.49
     Click
    -0.48
     Cientí
    -0.48
    Conclusie
    -0.47
     épis
    -0.46
     spé
    -0.46
    Clicked
    -0.44
    POSITIVE LOGITS
     environment
    1.16
     Environment
    1.04
    environment
    1.03
     ENVIRONMENT
    1.01
    Environment
    0.98
    vironment
    0.95
     Environments
    0.93
    Environ
    0.92
     environ
    0.90
    ENVIRONMENT
    0.90
    Activations Density 0.083%

    No Known Activations