© 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. 28-GEMMASCOPE-RES-16K
    6. 9053
    Prev
    Next
    INDEX
    Explanations

    references to academic or research engagement activities

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

    Follows punctuation or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    either/or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     absch
    -0.25
     verdade
    -0.24
    циони
    -0.23
     shi
    -0.23
     ajuns
    -0.22
     Voraus
    -0.22
    ないと
    -0.22
     ga
    -0.21
     declarat
    -0.21
     pass
    -0.21
    POSITIVE LOGITS
    either
    1.00
    Either
    0.98
     maybe
    0.98
     either
    0.97
    perhaps
    0.97
     perhaps
    0.95
    Maybe
    0.94
    maybe
    0.93
     Either
    0.90
     Maybe
    0.89
    Activations Density 0.405%

    No Known Activations