Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8619
    Prev
    Next
    INDEX
    Explanations

    references to collective accountability or shared experiences

    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
    ViewFeatures
    -0.91
     ExecuteAsync
    -0.85
    styleType
    -0.85
     CreateTagHelper
    -0.84
     TestBed
    -0.83
    VersionUID
    -0.81
    Véxase
    -0.75
     ISNI
    -0.75
    WebVitals
    -0.75
    twimg
    -0.73
    POSITIVE LOGITS
    中略
    0.61
    脚注の使い方
    0.52
     abstrait
    0.52
     fallecido
    0.50
     sauvage
    0.48
     altrimenti
    0.48
     baisse
    0.48
     multicolore
    0.48
     nameof
    0.47
     frequenza
    0.47
    Activations Density 0.098%

    No Known Activations