© 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. 11-GEMMASCOPE-RES-16K
    11. 4910
    Prev
    Next
    INDEX
    Explanations

    conclusions or summarizing statements at the end of sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    withIdentifier
    -0.50
    intios
    -0.48
    cabulary
    -0.48
    </thead>
    -0.48
     ReSharper
    -0.47
    PageFactory
    -0.47
    rxjs
    -0.47
    stags
    -0.47
     Skyl
    -0.46
     EventArgs
    -0.45
    POSITIVE LOGITS
     ultimately
    1.06
     Ultimately
    1.02
    Ultimately
    0.99
     ultimate
    0.98
    最终
    0.94
    最終
    0.90
     uiteindelijk
    0.83
     final
    0.81
    最後は
    0.81
    Final
    0.79
    Activations Density 0.559%

    No Known Activations