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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 99677
    Prev
    Next
    INDEX
    Explanations

    references to specific functions or libraries in programming, particularly related to text handling and user interface elements

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

    Schleswig and Holstein

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     "..\..\..\
    -0.42
     komma
    -0.38
     kişi
    -0.32
     "..\..\
    -0.32
     citoy
    -0.31
     entrée
    -0.31
     ček
    -0.30
    dp
    -0.30
     Percival
    -0.30
     باشد
    -0.29
    POSITIVE LOGITS
    concatenate
    1.77
    vstack
    1.16
     contextLoads
    1.06
    DockStyle
    0.88
     concatenate
    0.81
     LoggerFactory
    0.73
    makeConstraints
    0.73
     handleMessage
    0.71
     MotionEvent
    0.69
     FetchType
    0.68
    Activations Density 0.006%

    No Known Activations