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. 20-GEMMASCOPE-RES-16K
    6. 14023
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions and their management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     freue
    -0.51
     conmigo
    -0.48
     comigo
    -0.48
     EnglishChoose
    -0.45
     sija
    -0.44
     nostru
    -0.44
     tää
    -0.44
     nôtre
    -0.43
    jublj
    -0.43
     Geset
    -0.42
    POSITIVE LOGITS
    MessageOf
    0.94
    LookAnd
    0.94
     transférez
    0.91
    Sucesor
    0.88
    bewerken
    0.87
    adpleegd
    0.85
    abestanden
    0.84
    oredCriteria
    0.83
    ValueStyle
    0.83
    XmlEnum
    0.81
    Activations Density 2.333%

    No Known Activations