© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 9490
    Prev
    Next
    INDEX
    Explanations

    references to leadership changes and political replacements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.71
     disambiguazione
    -0.70
    IBOutlet
    -0.69
     deſt
    -0.61
    initializeApp
    -0.61
    AddTagHelper
    -0.59
     ſet
    -0.58
     ſhould
    -0.58
    iomanip
    -0.58
     ſp
    -0.58
    POSITIVE LOGITS
     những
    0.52
     qualified
    0.52
     ऐसे
    0.49
     olyan
    0.49
     one
    0.47
    complexContent
    0.44
     a
    0.44
     certified
    0.43
     someone
    0.42
     highly
    0.41
    Activations Density 0.437%

    No Known Activations