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. 4-GEMMASCOPE-RES-16K
    6. 16001
    Prev
    Next
    INDEX
    Explanations

    commands related to task scheduling and management in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laşı
    -0.52
    ríamos
    -0.52
    BarStyle
    -0.51
     Nah
    -0.50
     getField
    -0.49
    LLocation
    -0.48
    engelsk
    -0.48
    始まり
    -0.48
     Khal
    -0.48
    ?";
    -0.47
    POSITIVE LOGITS
    RenderAtEndOf
    0.77
    staticmethod
    0.69
    $_['
    0.67
    GMENT
    0.65
    )\}
    0.64
    ブレム
    0.63
     EconPapers
    0.63
     تضيفلها
    0.63
    OGND
    0.62
     ͡°)
    0.62
    Activations Density 0.128%

    No Known Activations