© 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. 9-GEMMASCOPE-RES-16K
    11. 9439
    Prev
    Next
    INDEX
    Explanations

    references to checkerboard or lattice structures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    visual/graphical elements like pixels, blocks, lattices, and grid-based structures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝗫
    -0.44
    план
    -0.42
    illères
    -0.42
     Roskov
    -0.42
    ValueStyle
    -0.42
    ScopeManager
    -0.41
     PLANS
    -0.40
    もしろ
    -0.40
    monės
    -0.40
    WaitGroup
    -0.39
    POSITIVE LOGITS
    PutPixel
    0.84
     pixels
    0.53
     pixel
    0.52
     Pixels
    0.50
     Pixel
    0.49
    Pixel
    0.48
    pixel
    0.46
    像素
    0.45
    Pixels
    0.44
    pixels
    0.43
    Activations Density 0.506%

    No Known Activations