© 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. 3-GEMMASCOPE-RES-16K
    6. 5582
    Prev
    Next
    INDEX
    Explanations

    references to individuals who held previous official positions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
     pleaſure
    -0.59
    WritableDatabase
    -0.57
    DataAnnotations
    -0.56
    zerland
    -0.56
     вікісторінку
    -0.55
    eclampsia
    -0.54
    IntoConstraints
    -0.54
     lyre
    -0.53
    uey
    -0.52
    SBATCH
    -0.52
    POSITIVE LOGITS
     former
    4.25
    Former
    3.73
     Former
    3.72
    former
    3.56
     ehemalige
    2.78
     ehemaligen
    2.70
     býval
    2.48
     ehemal
    2.39
     mantan
    2.28
     formerly
    2.19
    Activations Density 0.049%

    No Known Activations