© 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-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 11280
    Prev
    Next
    INDEX
    Explanations

    references to forms in the context of programming, specifically within the Windows Forms and Swing frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     Außer
    -0.42
     Pij
    -0.40
    pij
    -0.40
    配
    -0.38
    YOND
    -0.36
     Noch
    -0.36
    đu
    -0.35
    dirond
    -0.35
     Übernach
    -0.35
    gjenge
    -0.35
    POSITIVE LOGITS
    Forms
    2.55
     Forms
    2.13
     forms
    1.72
     FORMS
    1.71
    forms
    1.70
    FORMS
    1.51
     Formen
    1.22
     Form
    1.21
     formes
    1.20
     formas
    1.10
    Activations Density 0.026%

    No Known Activations