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. 21-GEMMASCOPE-RES-16K
    6. 15302
    Prev
    Next
    INDEX
    Explanations

    technical details related to automotive transmission systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataAnnotations
    -0.58
    Composable
    -0.56
    PerformLayout
    -0.56
    MENAFN
    -0.54
    enumi
    -0.53
     kaarangay
    -0.52
    はじめに
    -0.50
     Avez
    -0.49
    Jeografia
    -0.46
    BeginContext
    -0.46
    POSITIVE LOGITS
     mode
    2.16
     Mode
    1.90
     modes
    1.77
    mode
    1.76
    Mode
    1.74
     MODE
    1.72
    MODE
    1.59
     Modes
    1.55
    modes
    1.49
    モード
    1.48
    Activations Density 0.327%

    No Known Activations