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. 5-GEMMASCOPE-RES-16K
    6. 2917
    Prev
    Next
    INDEX
    Explanations

    references to dedication or commitment, particularly in a professional or passionate context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.74
    MigrationBuilder
    -0.72
    ApiModel
    -0.71
    +:+
    -0.71
    PreferredItem
    -0.68
    complexContent
    -0.65
    rlpool
    -0.64
     PhpStorm
    -0.64
    angi
    -0.63
     Airways
    -0.62
    POSITIVE LOGITS
     dedicated
    2.25
    dedicated
    2.14
    Dedicated
    2.10
     Dedicated
    2.04
     dedicate
    2.02
     dedic
    1.87
     dedication
    1.83
     dedicado
    1.79
     devoted
    1.74
     dédié
    1.73
    Activations Density 0.051%

    No Known Activations