© 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. 16-GEMMASCOPE-RES-16K
    11. 9318
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming references related to data management and API interactions

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

    Code-related abbreviations and acronyms

    np_acts-logits-general · gemini-2.0-flash

    traindata

    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
     dí
    -0.45
     linear
    -0.45
     désolés
    -0.44
     parcela
    -0.43
     large
    -0.42
     press
    -0.42
    尼斯
    -0.42
    까지
    -0.41
    ?
    -0.41
    -
    -0.41
    POSITIVE LOGITS
    SharedCtor
    0.78
    ulemon
    0.74
     AppCompatTheme
    0.71
    aarrggbb
    0.69
    GIVEREF
    0.68
    RTEX
    0.68
    PerformLayout
    0.63
    RegressionTest
    0.63
    يكب
    0.60
     Sabha
    0.59
    Activations Density 0.368%

    No Known Activations