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. 13-GEMMASCOPE-RES-16K
    6. 89
    Prev
    Next
    INDEX
    Explanations

    references to various types of code structures and conditions

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

    terms and identifiers related to programming and computer science concepts, particularly focusing on acronyms or technical terms frequently used in code.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.68
     <<<<<<<<<<<<<<
    -0.65
     administrativos
    -0.61
     יום
    -0.60
    Compartir
    -0.57
     decidido
    -0.56
     Италијани
    -0.55
    UTERS
    -0.53
    presto
    -0.53
    numerusform
    -0.53
    POSITIVE LOGITS
    IBLIO
    0.82
    neſs
    0.78
    ſo
    0.78
    zegor
    0.76
     Diſ
    0.76
     phal
    0.72
     Conſ
    0.71
     caes
    0.71
    ghijklmnop
    0.71
     Expl
    0.71
    Activations Density 0.337%

    No Known Activations