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. 2-GEMMASCOPE-RES-16K
    6. 6616
    Prev
    Next
    INDEX
    Explanations

    references to database rows and columns in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.83
     estekak
    -0.68
    ={()=>
    -0.66
    mapStateToProps
    -0.61
    ="#"><
    -0.61
     }}"></
    -0.61
    HomeAsUp
    -0.60
    endpush
    -0.59
    ellants
    -0.59
    /******/
    -0.58
    POSITIVE LOGITS
    rows
    2.88
    Rows
    2.69
     rows
    2.40
     Rows
    2.13
    ROWS
    1.74
    cols
    1.23
     filas
    1.16
     columns
    1.05
    filas
    1.00
    numRows
    0.99
    Activations Density 0.104%

    No Known Activations