© 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 - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15327
    Prev
    Next
    INDEX
    Explanations

    coding elements related to GUI programming and event handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.83
    AutoSize
    -0.83
    +#+
    -0.75
    
    -0.70
    WriteTagHelper
    -0.68
    RTCF
    -0.65
    UnusedPrivate
    -0.62
    enderror
    -0.62
    IsMutable
    -0.62
    ValueStyle
    -0.60
    POSITIVE LOGITS
    jPanel
    2.44
     jPanel
    1.14
    jButton
    1.12
    ActionPerformed
    1.00
    RequestMapping
    0.96
    groupBox
    0.90
    uParam
    0.85
    jScrollPane
    0.82
    startActivity
    0.79
    jTextField
    0.78
    Activations Density 0.015%

    No Known Activations