© 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. 2086
    Prev
    Next
    INDEX
    Explanations

    references to meetings and discussions involving community or governmental entities

    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
     primacy
    -0.40
     nuanced
    -0.39
     kasarigan
    -0.39
     utterly
    -0.35
     transformative
    -0.35
     sophisticated
    -0.33
     Soho
    -0.33
     diep
    -0.33
     sobretudo
    -0.33
     methodological
    -0.32
    POSITIVE LOGITS
     
    0.72
     ***!
    0.71
    rawDesc
    0.64
    IntoConstraints
    0.63
    存于互联网档案馆
    0.62
    PyExc
    0.61
    domada
    0.61
     employes
    0.60
    ########.
    0.59
    parsedMessage
    0.59
    Activations Density 0.293%

    No Known Activations