© 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. 31-GEMMASCOPE-RES-16K
    6. 9697
    Prev
    Next
    INDEX
    Explanations

    scientific comparisons and measurements of orders of magnitude

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

    phrases indicating large numerical differences, particularly "by/more than/an order of magnitude".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    expressions describing comparisons between numerical magnitudes or orders of magnitude.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChromeDriver
    -0.68
    RegressionTest
    -0.63
    fjspx
    -0.62
    setVerticalGroup
    -0.61
    twimg
    -0.61
    awtextra
    -0.61
    ValueStyle
    -0.57
    ponses
    -0.57
     CreateTagHelper
    -0.57
    utilisons
    -0.56
    POSITIVE LOGITS
     notch
    0.73
     step
    0.72
     notches
    0.69
    step
    0.63
     orders
    0.62
     two
    0.56
    notch
    0.56
     steps
    0.54
     one
    0.53
    one
    0.52
    Activations Density 0.369%

    No Known Activations