© 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. 33-GEMMASCOPE-RES-16K
    6. 12271
    Prev
    Next
    INDEX
    Explanations

    warnings and cautions related to content safety and system errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ExecuteReader
    -0.36
    contentPane
    -0.29
    szönöm
    -0.28
    BagLayout
    -0.28
    Koordinaten
    -0.28
     bezeichneter
    -0.27
    InlineData
    -0.26
    GetValue
    -0.26
    SharedCtor
    -0.26
    principalColumn
    -0.26
    POSITIVE LOGITS
     warning
    3.33
     warnings
    3.05
     Warning
    2.89
     warn
    2.83
     warned
    2.73
    warning
    2.70
     warns
    2.64
    Warning
    2.59
     Warnings
    2.58
    警告
    2.53
    Activations Density 0.634%

    No Known Activations