© 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. 28-GEMMASCOPE-RES-16K
    11. 4107
    Prev
    Next
    INDEX
    Explanations

    phrases indicating singular and unique entities or events

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

    "Single" or "one" related words

    np_acts-logits-general · gemini-2.0-flash

    single stage, single shot

    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
    awtextra
    -0.68
     '\\;'
    -0.60
     otomatig
    -0.54
     referrerpolicy
    -0.54
     Wikimedijinoj
    -0.49
    XMLSchema
    -0.48
     nahilalakip
    -0.48
     nakalista
    -0.47
    Diwedd
    -0.46
     CreateTagHelper
    -0.46
    POSITIVE LOGITS
     single
    0.52
     Одно
    0.50
     hundred
    0.46
     sided
    0.45
     одно
    0.43
     Single
    0.42
     univ
    0.40
     uni
    0.40
     semester
    0.39
     thousand
    0.39
    Activations Density 0.331%

    No Known Activations