© 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
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 712
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure related to task management

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

    azure container registry commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    windowFixed
    -0.53
    setVerticalGroup
    -0.43
    richTextPanel
    -0.37
    AddHtmlAttribute
    -0.36
     ExecuteAsync
    -0.35
    parsedMessage
    -0.34
     nhàng
    -0.34
    ✭✭
    -0.32
    adaptiveStyles
    -0.32
     natin
    -0.32
    POSITIVE LOGITS
    BeginInit
    0.55
     gouver
    0.49
     administration
    0.48
     admin
    0.48
     administrator
    0.47
     administrators
    0.46
     Admin
    0.46
    nezeu
    0.46
     messages
    0.45
     Trainers
    0.45
    Activations Density 0.010%

    No Known Activations