© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 16372
    Prev
    Next
    INDEX
    Explanations

    identifiable entities and headings in structured content like lists and outlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     her
    -0.55
    .
    -0.52
     lagi
    -0.50
     to
    -0.47
     them
    -0.46
     gran
    -0.45
    ortunadamente
    -0.45
    COUVER
    -0.45
     would
    -0.44
     do
    -0.44
    POSITIVE LOGITS
    ChildScrollView
    0.93
     ostavi
    0.93
    SequentialGroup
    0.89
    Personensuche
    0.86
    GEBURTSDATUM
    0.84
    StructEnd
    0.83
    #+#
    0.80
    ⓧ
    0.80
    WithIOException
    0.77
     poffible
    0.76
    Activations Density 1.199%

    No Known Activations