© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 8585
    Prev
    Next
    INDEX
    Explanations

    references to programming frameworks and libraries, specifically those related to Django and version control systems like Git

    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
     CreateTagHelper
    -1.04
     Zusatz
    -0.31
     Barros
    -0.29
    原始内容存档于
    -0.28
     dass
    -0.28
     Neben
    -0.27
    isEqualTo
    -0.27
     primit
    -0.27
     Lohn
    -0.27
    getInfo
    -0.26
    POSITIVE LOGITS
    ScopeManager
    6.91
    SourceChecksum
    1.38
    TagHelper
    1.25
    jspx
    1.23
     wireType
    1.09
    fjspx
    1.08
    parsedMessage
    1.00
    AccessorTable
    0.96
    AnchorStyles
    0.95
    +#+#
    0.89
    Activations Density 0.003%

    No Known Activations