© 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. 40-GEMMASCOPE-RES-16K
    6. 1990
    Prev
    Next
    INDEX
    Explanations

    programming-related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InstrumentedTest
    -0.46
     مشين
    -0.45
    XmlRootElement
    -0.44
     ModelExpression
    -0.44
     propOrder
    -0.43
    WebMethod
    -0.41
     LEYENDO
    -0.40
    AccessorTable
    -0.40
     MediatR
    -0.39
    WithMany
    -0.38
    POSITIVE LOGITS
     bold
    0.70
     terminal
    0.69
     underline
    0.68
    Bold
    0.66
    bold
    0.65
     Terminal
    0.65
     curses
    0.64
    Terminal
    0.62
     Bold
    0.62
     underlined
    0.62
    Activations Density 0.662%

    No Known Activations