© 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. 9-GEMMASCOPE-RES-16K
    6. 8797
    Prev
    Next
    INDEX
    Explanations

    references to coded or structured data formats and documents, particularly in a programming or markup context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.81
     Infórmanos
    -0.81
    complexContent
    -0.80
     propOrder
    -0.75
    RTCK
    -0.73
    WriteTagHelper
    -0.72
    TagMode
    -0.72
    ftagPool
    -0.71
    Autoritní
    -0.70
    MemoryWarning
    -0.70
    POSITIVE LOGITS
     asisti
    0.32
     besonder
    0.32
     asociado
    0.31
    中的
    0.30
     commonly
    0.30
     domestique
    0.29
     dianteira
    0.29
     conocen
    0.29
     Provinsi
    0.29
     роз
    0.29
    Activations Density 0.698%

    No Known Activations