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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16023
    Prev
    Next
    INDEX
    Explanations

    specific patterns or formats in data structures, particularly those related to JSON or serialized objects

    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
     &___
    -0.60
     transfieras
    -0.55
     amico
    -0.52
     prêtre
    -0.51
    käse
    -0.50
     étanche
    -0.50
     ennemi
    -0.49
     arrière
    -0.48
    Biblia
    -0.48
    ിയ
    -0.47
    POSITIVE LOGITS
     MenuView
    0.69
    WebVitals
    0.60
    extAlignment
    0.56
    rict
    0.55
     jsPsych
    0.55
     GenerationType
    0.54
     ExecuteAsync
    0.54
    ########.
    0.53
    forRoot
    0.52
     Wikimedijinoj
    0.51
    Activations Density 0.493%

    No Known Activations