© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12417
    Prev
    Next
    INDEX
    Explanations

    terms related to data management and state restoration in software

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

    Saving/restoring state, configuration, or backup

    np_acts-logits-general · gemini-2.0-flash

    saving and restoring state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isContained
    -0.53
    hematics
    -0.47
     InputDecoration
    -0.46
    plates
    -0.46
    InputBorder
    -0.45
    ंदीखरीदारी
    -0.44
    matchCondition
    -0.44
    ollectionView
    -0.44
    hoeddwyd
    -0.43
     reflexive
    -0.42
    POSITIVE LOGITS
     Roskov
    0.57
     onSave
    0.37
    GIO
    0.37
     mem
    0.37
    NameInMap
    0.36
    save
    0.36
    保存
    0.36
    ukkig
    0.35
     mema
    0.35
    SAV
    0.35
    Activations Density 0.266%

    No Known Activations