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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38843
    Prev
    Next
    INDEX
    Explanations

    variables and function names in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     asti
    -0.51
     negatively
    -0.51
    áját
    -0.50
    pholes
    -0.50
    ]='\
    -0.48
     educativas
    -0.47
    iffance
    -0.47
     kiin
    -0.47
    tenti
    -0.46
    ListOf
    -0.45
    POSITIVE LOGITS
     InputDecoration
    0.85
    IsMutable
    0.77
    Tikang
    0.73
    Legături
    0.72
     LCCN
    0.65
    Населення
    0.65
     المعيارى
    0.64
     يتيمه
    0.63
     Вікі
    0.63
    StoryboardSegue
    0.63
    Activations Density 0.210%

    No Known Activations