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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 77205
    Prev
    Next
    INDEX
    Explanations

    words related to launching or the act of launching something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    TestBed
    -0.60
     defStyle
    -0.54
     TestBed
    -0.53
    ••••
    -0.49
     propOrder
    -0.47
    ebi
    -0.47
     quiser
    -0.47
    addAttribute
    -0.47
     Normdatei
    -0.46
    endregion
    -0.46
    POSITIVE LOGITS
     Launch
    0.92
    Launch
    0.88
     LAUNCH
    0.85
    LAUNCH
    0.82
    launch
    0.81
     launch
    0.81
    launcher
    0.73
     Launcher
    0.72
    Launcher
    0.71
     launcher
    0.69
    Activations Density 0.004%

    No Known Activations