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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 12042
    Prev
    Next
    INDEX
    Explanations

    references to performance metrics and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "performance" and related concepts

    np_acts-logits-general · gemini-2.0-flash

    performance quality and evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comigo
    -0.82
     فريبيس
    -0.81
    InputBorder
    -0.80
     للمعارف
    -0.77
    PathVariable
    -0.76
    IsPostBack
    -0.72
     vacanze
    -0.72
     larmes
    -0.71
     gioia
    -0.69
     Kingfisher
    -0.69
    POSITIVE LOGITS
     performances
    1.30
     performance
    1.26
     Performance
    1.13
     Performances
    1.10
    Performance
    1.05
    Performances
    1.03
    PERFORMANCE
    1.02
    perform
    1.01
     perform
    1.01
    performance
    1.01
    Activations Density 0.117%

    No Known Activations