© 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. 7925
    Prev
    Next
    INDEX
    Explanations

    conjunctions and references to relationships or interactions

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

    "Etc.", "and so on", or similar list continuations

    np_acts-logits-general · gemini-2.0-flash

    lists and enumerations

    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
    Personendaten
    -0.45
     tevens
    -0.40
    ródło
    -0.40
     isKindOfClass
    -0.40
    何况
    -0.39
    nextProps
    -0.39
     bereiken
    -0.37
    >{"
    -0.37
    standes
    -0.36
     =
    
    -0.35
    POSITIVE LOGITS
     whatnot
    1.30
     etc
    1.24
     such
    1.20
     stuff
    1.20
    etc
    1.05
    之类的
    0.98
    such
    0.97
     blah
    0.97
     Etc
    0.96
    Etc
    0.93
    Activations Density 0.267%

    No Known Activations