© 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. 18-GEMMASCOPE-RES-16K
    11. 14064
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terms relating to geometry and linear equations

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

    Lines, slopes, and planes in mathematical contexts

    np_acts-logits-general · gemini-2.0-flash

    lines and slopes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <>",
    -0.63
     size
    -0.60
    ाहरण
    -0.59
     Size
    -0.59
    Size
    -0.58
     sizes
    -0.56
     sized
    -0.56
    Sizes
    -0.52
    sized
    -0.51
     Sizes
    -0.51
    POSITIVE LOGITS
     slope
    0.88
     line
    0.88
     lines
    0.86
     Lines
    0.80
     Line
    0.79
    slope
    0.76
     Slope
    0.75
    Lines
    0.75
     slopes
    0.75
    Slope
    0.71
    Activations Density 0.540%

    No Known Activations