Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 12011
    Prev
    Next
    INDEX
    Explanations

    procedural instructions or steps in a guide or tutorial format

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

    Beginning/introducing words (first, simply, firstly)

    np_acts-logits-general · gemini-2.0-flash

    simply or first

    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
     further
    -0.59
     VizieR
    -0.57
    клопе
    -0.56
    GraphicsUnit
    -0.56
     consumption
    -0.54
    further
    -0.52
     insuffisamment
    -0.51
    اعمال
    -0.49
    IBOutlet
    -0.49
    ReadInt
    -0.49
    POSITIVE LOGITS
     StatefulWidget
    0.90
    Simply
    0.68
    まず
    0.65
    Firstly
    0.64
     einfach
    0.61
     Simply
    0.61
    首先
    0.61
     Firstly
    0.59
    はじめに
    0.58
     simplement
    0.56
    Activations Density 0.541%

    No Known Activations