© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1292
    Prev
    Next
    INDEX
    Explanations

    references to technical details concerning API authentication and integration processes

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

    account logins and sign-ins

    np_acts-logits-general · gemini-2.0-flash

    Facebook account kit login

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     budgeting
    -0.37
    AndroidJUnit
    -0.32
    Budget
    -0.31
    breathing
    -0.31
     Budget
    -0.31
     budget
    -0.31
    greSQL
    -0.31
     Budgets
    -0.30
     AutoCAD
    -0.30
    fitting
    -0.30
    POSITIVE LOGITS
    AnchorTagHelper
    0.61
    $_['
    0.61
    ServletException
    0.60
    onActivityResult
    0.57
    IndentedString
    0.57
     فريبيس
    0.56
    UserScript
    0.56
     nonUne
    0.55
    AccessorTable
    0.54
    Autoritní
    0.54
    Activations Density 0.177%

    No Known Activations