Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12029
    Prev
    Next
    INDEX
    Explanations

    references to problems, issues, and questions relating to various contexts, particularly focusing on law and society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.81
    gbaar
    -0.80
     ExecuteAsync
    -0.76
    GraphicsUnit
    -0.74
     StringTokenizer
    -0.72
     $[-
    -0.71
    ApplicationTests
    -0.71
    AutoScaleMode
    -0.70
     ControllerBase
    -0.70
     doInBackground
    -0.68
    POSITIVE LOGITS
     وتسجيلات
    0.51
     administrativos
    0.50
     civiles
    0.50
     åt
    0.46
    grao
    0.45
     tắt
    0.44
     fermés
    0.43
     llorando
    0.42
     langit
    0.41
     culturelles
    0.41
    Activations Density 0.742%

    No Known Activations