© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 197
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to programming or data structures

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

    Code, results, or statistics

    np_acts-logits-general · gemini-2.0-flash

    generated results

    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
    ParallelGroup
    -0.61
    zzleHttp
    -0.60
    PullParser
    -0.59
    IntoConstraints
    -0.59
    rawDesc
    -0.57
     snippetHide
    -0.57
     }}"></
    -0.55
    fjspx
    -0.52
     protoimpl
    -0.52
     الحره
    -0.51
    POSITIVE LOGITS
     GENERATED
    0.45
     generated
    0.42
     hasil
    0.40
     results
    0.39
    Generated
    0.39
     developed
    0.39
     pós
    0.39
     already
    0.39
     résultats
    0.38
     Resultados
    0.38
    Activations Density 1.624%

    No Known Activations