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

    Neuronpedia

    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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13418
    Prev
    Next
    INDEX
    Explanations

    function calls for UI element interactions in programming

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

    method calls on Android resource objects using the findViewById and getString patterns.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ServletConfig
    -0.43
     Autorisations
    -0.40
    Captor
    -0.39
    ForRow
    -0.39
     للمعارف
    -0.37
    Hochspringen
    -0.37
    rungsseite
    -0.35
     mío
    -0.35
    rshire
    -0.35
     Füßen
    -0.35
    POSITIVE LOGITS
     R
    0.94
    R
    0.75
     resource
    0.52
    resourceId
    0.50
    setContentView
    0.50
     Resource
    0.49
    Resource
    0.45
     Ressource
    0.43
     D
    0.43
    лтамалар
    0.41
    Activations Density 0.093%

    No Known Activations