© 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. 12-GEMMASCOPE-RES-16K
    6. 5203
    Prev
    Next
    INDEX
    Explanations

    references to advocacy and community-focused initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.64
     HttpNotFound
    -0.58
    期刊论文
    -0.55
    DeleteBehavior
    -0.54
    utives
    -0.50
    slidesToShow
    -0.50
    LoadScene
    -0.49
     StatefulWidget
    -0.48
    apatalk
    -0.48
    édie
    -0.48
    POSITIVE LOGITS
     advocacy
    0.79
     Advocacy
    0.77
    Advoc
    0.72
    advoc
    0.66
     advocate
    0.66
     lobbying
    0.61
     advocating
    0.60
     advocates
    0.57
     Advoc
    0.55
     Advocate
    0.52
    Activations Density 0.434%

    No Known Activations