© 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. 7116
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms related to measurement and analysis

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

    languages other than English

    np_acts-logits-general · gemini-2.0-flash

    non-component, non-mitogenic, non-volatile

    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
     ujednoznacz
    -0.76
    ⓧ
    -0.66
     <<<<<<<<<<<<<<
    -0.61
     nahilalakip
    -0.57
     Strain
    -0.54
    OfBirth
    -0.54
    Litteratur
    -0.54
    strain
    -0.54
    Strain
    -0.53
    ropriate
    -0.52
    POSITIVE LOGITS
     Porém
    0.31
    则
    0.30
    usercontent
    0.30
     zaś
    0.30
     natomiast
    0.30
     hingegen
    0.28
    則
    0.28
     however
    0.28
    новништво
    0.27
    setVerticalGroup
    0.26
    Activations Density 0.857%

    No Known Activations