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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6862
    Prev
    Next
    INDEX
    Explanations

    references to decisions, resolutions, and approvals by governing bodies

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

    Approval, agreement, or decisions

    np_acts-logits-general · gemini-2.0-flash

    formal decisions and agreements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MethodManager
    -0.50
    CGPoint
    -0.40
     MyApp
    -0.40
     vle
    -0.37
     metric
    -0.37
    IKit
    -0.37
     OnTrigger
    -0.36
    Diwedd
    -0.36
    cademia
    -0.36
    atown
    -0.36
    POSITIVE LOGITS
     unanimously
    0.79
     voted
    0.62
     unanimous
    0.62
     Beschluss
    0.60
     vote
    0.58
     resolution
    0.56
    rungsseite
    0.52
     decision
    0.52
     resolución
    0.52
     Signalez
    0.50
    Activations Density 0.425%

    No Known Activations