© 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. 20-GEMMASCOPE-RES-16K
    11. 12721
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "second," including related context such as derivatives and order in mathematical discussions

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

    ordinal numbers like "second", "third" often followed by nouns or measurements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Luv
    -0.49
    Relief
    -0.47
     Buchen
    -0.45
     Luv
    -0.45
     comigo
    -0.44
    mActivity
    -0.44
    UCLA
    -0.43
     ello
    -0.43
    BMI
    -0.43
     gearbeitet
    -0.42
    POSITIVE LOGITS
     third
    1.15
     second
    1.12
     SECOND
    1.04
     THIRD
    1.00
     Third
    0.96
     Second
    0.95
     fourth
    0.94
     fifth
    0.94
    Third
    0.91
    Second
    0.89
    Activations Density 0.112%

    No Known Activations