© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 1242
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface buttons and actions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.58
     يتيمه
    -0.53
    الحياه
    -0.52
    parsedMessage
    -0.47
    MessageState
    -0.46
     MonoBehaviour
    -0.45
     *__
    -0.44
    elemField
    -0.43
     getItemId
    -0.42
    webElementXpaths
    -0.41
    POSITIVE LOGITS
     cancel
    1.08
     Cancel
    1.04
    Cancel
    1.01
     OK
    0.95
    cancel
    0.93
     CANCEL
    0.92
     close
    0.91
     Exit
    0.90
     exit
    0.90
     Close
    0.89
    Activations Density 0.363%

    No Known Activations