© 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. 6-GEMMASCOPE-RES-16K
    11. 5618
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to design and appearance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UniformLocation
    -0.62
     noDo
    -0.61
     jdbcTemplate
    -0.61
    GEBURTSDATUM
    -0.60
     colitis
    -0.60
    StandardCharsets
    -0.57
     Jimi
    -0.57
     Yunnan
    -0.56
     patches
    -0.56
     Theſe
    -0.55
    POSITIVE LOGITS
     shape
    1.24
     Shape
    1.05
     shapes
    1.03
     SHAPE
    1.02
    shape
    1.02
     silhouette
    0.94
    shapes
    0.91
    hape
    0.90
     silueta
    0.89
    Shape
    0.88
    Activations Density 0.382%

    No Known Activations