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. 5-GEMMASCOPE-RES-16K
    6. 15996
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the act of launching or initiating something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oneofs
    -0.75
    EReference
    -0.67
     cref
    -0.66
     Motel
    -0.62
    ENCOD
    -0.62
    verwijspagina
    -0.62
     &___
    -0.62
    okhttp
    -0.61
    styleType
    -0.60
    Vegas
    -0.60
    POSITIVE LOGITS
     LAUNCH
    2.33
     launch
    2.32
     launches
    2.19
     Launch
    2.17
    Launch
    2.14
     launched
    2.14
    launch
    2.06
    Launching
    2.04
     Launches
    1.98
    LAUNCH
    1.97
    Activations Density 0.056%

    No Known Activations