© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16345
    Prev
    Next
    INDEX
    Explanations

    references to statistical concepts or functions related to probability or mathematical modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    
    -0.45
     mach
    -0.43
     NSError
    -0.41
    ErrUnexpectedEOF
    -0.40
     RP
    -0.39
     CPP
    -0.37
    ....)
    -0.36
     &___
    -0.35
     zer
    -0.35
     VHS
    -0.35
    POSITIVE LOGITS
    PointerException
    0.50
    uride
    0.48
    ViewImports
    0.44
    cortico
    0.43
    tagext
    0.42
    ItemBackground
    0.41
    styleType
    0.40
    acamata
    0.40
     descar
    0.40
    dafx
    0.39
    Activations Density 0.807%

    No Known Activations