© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9734
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reform" and certain code-like phrases or patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     considered
    -0.34
     touch
    -0.34
     do
    -0.31
     produced
    -0.31
     action
    -0.28
     have
    -0.27
     press
    -0.27
     said
    -0.27
     round
    -0.27
     consider
    -0.25
    POSITIVE LOGITS
     surla
    1.02
     المعيارى
    0.90
    interopRequire
    0.88
     verſch
    0.85
    keyColumn
    0.84
     パンチラ
    0.83
     unſer
    0.83
    tvguidetime
    0.83
     beſch
    0.83
     AssemblyTitle
    0.83
    Activations Density 0.405%

    No Known Activations