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. 2227
    Prev
    Next
    INDEX
    Explanations

    function arguments and parameter definitions in programming code

    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
    expandindo
    -0.74
     packageName
    -0.66
    ")->
    -0.66
     Majefty
    -0.66
    koneksi
    -0.65
    )");
    
    -0.65
     riuscito
    -0.64
     accessToken
    -0.63
     itſelf
    -0.63
    :~
    -0.63
    POSITIVE LOGITS
    arg
    3.30
     arg
    2.89
    Arg
    2.27
     Arg
    2.22
    ARG
    2.04
     ARG
    1.66
    args
    1.33
     Argus
    1.28
     args
    1.25
    arga
    1.21
    Activations Density 0.039%

    No Known Activations