© 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. 13193
    Prev
    Next
    INDEX
    Explanations

    elements related to baseline or reference states in scientific contexts

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

    "Baseline" or initial states/conditions

    np_acts-logits-general · gemini-2.0-flash

    baseline conditions

    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
    WebElementEntity
    -0.62
     autorytatywna
    -0.60
     nonUne
    -0.58
    sizeCache
    -0.57
    exitRule
    -0.57
     Administrativna
    -0.57
    complexContent
    -0.57
    postIndex
    -0.56
     témoig
    -0.51
     continúas
    -0.50
    POSITIVE LOGITS
     pre
    0.47
    日常
    0.43
     rotina
    0.40
     normal
    0.39
     initial
    0.39
     baseline
    0.38
     daily
    0.37
     regular
    0.37
     mantenere
    0.37
    平时
    0.36
    Activations Density 0.961%

    No Known Activations