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. 2-GEMMASCOPE-RES-16K
    6. 3780
    Prev
    Next
    INDEX
    Explanations

    references to regression testing in a programming or software development context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    initializeApp
    -0.50
    </blockquote>
    -0.49
    ?";
    -0.49
    ³)
    -0.47
    czegó
    -0.47
    JsonInclude
    -0.47
    ixos
    -0.45
     dagegen
    -0.43
    ²)
    -0.42
    =""/>
    -0.42
    POSITIVE LOGITS
    ########.
    1.02
    able
    0.90
    RegressionTest
    0.78
    ABLE
    0.75
    mybatisplus
    0.72
    libft
    0.71
    :✨
    0.70
    Rüyada
    0.68
    cstdio
    0.66
    PerformLayout
    0.66
    Activations Density 2.238%

    No Known Activations