© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9601
    Prev
    Next
    INDEX
    Explanations

    references to technical methodologies or approaches in scientific contexts

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

    text about academic or scientific content, particularly when discussing research, methods, or systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    NameInMap
    -0.48
     estekak
    -0.46
     EconPapers
    -0.43
     OFDb
    -0.43
    WriteBarrier
    -0.43
    новниш
    -0.43
     Италијани
    -0.42
    bigsqcup
    -0.41
    EDEFAULT
    -0.40
     Exactos
    -0.40
    POSITIVE LOGITS
     مشين
    0.44
     prêtres
    0.42
    antMatchers
    0.42
     zimowa
    0.41
    balleur
    0.40
     snippetHide
    0.39
     similar
    0.38
    Similar
    0.38
    Климат
    0.38
    TestingModule
    0.36
    Activations Density 0.450%

    No Known Activations