© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 2092
    Prev
    Next
    INDEX
    Explanations

    configuration parameters and settings related to modes and types

    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
     EconPapers
    -0.54
    ########.
    -0.53
    AccessorTable
    -0.50
    ViewImports
    -0.50
    HasAnnotation
    -0.48
    InstrumentedTest
    -0.46
    AnimationsModule
    -0.43
    #+#
    -0.43
    SaveChangesAsync
    -0.42
     UIFont
    -0.42
    POSITIVE LOGITS
     none
    1.02
    none
    1.01
     None
    0.89
    None
    0.86
     NONE
    0.75
    NONE
    0.72
     ninguno
    0.66
     normal
    0.60
     manual
    0.60
    normal
    0.59
    Activations Density 1.029%

    No Known Activations