© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6647
    Prev
    Next
    INDEX
    Explanations

    phrases indicating repetition or continuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tarko
    -0.66
     tričko
    -0.65
     termica
    -0.65
     balení
    -0.63
     Füße
    -0.63
    iasaan
    -0.63
     hlavy
    -0.62
     öv
    -0.62
     høre
    -0.61
     mukana
    -0.61
    POSITIVE LOGITS
     another
    1.28
    another
    1.15
     ANOTHER
    1.09
     Another
    1.05
    Another
    1.02
    Otra
    0.68
    nother
    0.66
    另一个
    0.65
     Otra
    0.64
     a
    0.63
    Activations Density 0.080%

    No Known Activations