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. 9-GEMMASCOPE-RES-16K
    6. 908
    Prev
    Next
    INDEX
    Explanations

    references to popular culture and media events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SH
    -0.52
     term
    -0.52
     istilah
    -0.51
     yako
    -0.49
    </i>
    -0.45
     short
    -0.44
    ландия
    -0.44
     process
    -0.44
     ur
    -0.43
     experience
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.82
    enumi
    0.82
    tvguidetime
    0.81
    KommentareTeilen
    0.80
     وتسجيلات
    0.77
    RenderAtEndOf
    0.76
    .")
    
    0.75
     חיצוניים
    0.74
    InjectAttribute
    0.72
     surla
    0.71
    Activations Density 0.061%

    No Known Activations