© 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. 23-GEMMASCOPE-RES-16K
    11. 2242
    Prev
    Next
    INDEX
    Explanations

    sequences or patterns related to numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſch
    -0.63
    Бахар
    -0.59
    Referencies
    -0.57
    SharedCtor
    -0.56
     utafitiHapana
    -0.55
    slidesToShow
    -0.52
     setEmail
    -0.52
     SPI
    -0.51
     faſt
    -0.50
     propo
    -0.50
    POSITIVE LOGITS
     respiración
    0.54
     posibilidad
    0.51
    MessageTagHelper
    0.51
     typelib
    0.51
     orgánico
    0.49
     visibilidad
    0.46
     exportación
    0.45
     reflexión
    0.44
     mismas
    0.44
     financeiro
    0.44
    Activations Density 0.281%

    No Known Activations