© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4635
    Prev
    Next
    INDEX
    Explanations

    references to metadata in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chesse
    -0.68
     insuffisamment
    -0.67
     AssemblyVersion
    -0.66
     themſelves
    -0.65
     MonoBehaviour
    -0.65
    >
    -0.63
     Jefus
    -0.63
     Wikispecies
    -0.63
     Jes
    -0.62
     Kuj
    -0.62
    POSITIVE LOGITS
    metadata
    1.55
    Metadata
    1.53
     metadata
    1.51
     Metadata
    1.38
    METADATA
    0.89
     виправивши
    0.74
    rungsseite
    0.67
    LookAnd
    0.66
    rdf
    0.65
    ValuePair
    0.60
    Activations Density 0.103%

    No Known Activations