© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 6645
    Prev
    Next
    INDEX
    Explanations

    positive sentiments and support within a community context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
    )");
    -0.54
    )\}
    -0.52
    Ensuite
    -0.49
     ""))
    -0.49
     Electron
    -0.47
     Hardcore
    -0.47
     marginally
    -0.47
     chasse
    -0.47
     {}),
    -0.47
     Monfieur
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.81
     talent
    0.69
    +:+
    0.66
     فريبيس
    0.64
     snippetHide
    0.62
    脚注の使い方
    0.61
     tapped
    0.61
    Portale
    0.59
    ագրություններ
    0.59
     <",
    0.58
    Activations Density 0.226%

    No Known Activations