© 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. 22-GEMMASCOPE-RES-16K
    11. 6398
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and their relationships within scientific or technical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ObjectContext
    -0.40
    原始内容存档于
    -0.40
    WebMethod
    -0.38
    )}_{
    -0.36
    literals
    -0.36
    enumi
    -0.36
    printStackTrace
    -0.35
    )}_
    -0.35
     FixedUpdate
    -0.35
    ArgumentParser
    -0.35
    POSITIVE LOGITS
     propOrder
    0.64
     الحره
    0.60
     ujednoznacz
    0.57
    SharedDtor
    0.57
    webElementXpaths
    0.55
     pinulongan
    0.53
    oredCriteria
    0.50
    RTLR
    0.50
     nakalista
    0.50
    @[+][
    0.48
    Activations Density 1.686%

    No Known Activations