© 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. 23-GEMMASCOPE-RES-16K
    6. 2124
    Prev
    Next
    INDEX
    Explanations

    code structure and components related to user interface actions and event handling

    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
    KommentareTeilen
    -0.77
     مرئيه
    -0.73
     Italijanski
    -0.62
    RenderAtEndOf
    -0.61
     betweenstory
    -0.60
    UnusedPrivate
    -0.59
    expandindo
    -0.59
    IndentedString
    -0.57
    WaitGroup
    -0.57
     StringTokenizer
    -0.57
    POSITIVE LOGITS
    cabul
    0.45
    apimachinery
    0.43
     raw
    0.38
     bel
    0.36
     funds
    0.36
     Driscoll
    0.35
    ख्य
    0.35
     lī
    0.35
    ipfel
    0.35
    nrows
    0.34
    Activations Density 0.896%

    No Known Activations