© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 780
    Prev
    Next
    INDEX
    Explanations

    comparisons and similarities between different subjects or entities

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

    similarity or resemblance

    np_acts-logits-general · gemini-2.0-flash

    expressing similarity or resemblance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    atigable
    -0.53
    httphttps
    -0.52
    expandindo
    -0.49
    ⤹
    -0.48
    WaitGroup
    -0.44
    BagConstraints
    -0.44
    WriteBarrier
    -0.43
    Datuak
    -0.43
    marle
    -0.43
    hoodie
    -0.43
    POSITIVE LOGITS
     resemble
    0.77
     similar
    0.68
     resembles
    0.63
     resembled
    0.59
     resemblance
    0.59
     similarity
    0.59
     analogous
    0.59
     mirip
    0.58
     resembling
    0.55
     identical
    0.54
    Activations Density 0.805%

    No Known Activations