Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21-GEMMASCOPE-RES-16K
    6. 1929
    Prev
    Next
    INDEX
    Explanations

    instances of specific programming keywords and terms related to function and variable manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nenhuma
    -0.62
     žiad
    -0.62
     nicio
    -0.61
    ReusableCell
    -0.61
     voici
    -0.59
    RegressionTest
    -0.57
     particulières
    -0.55
     ninguno
    -0.55
     nenhum
    -0.54
    RectangleBorder
    -0.54
    POSITIVE LOGITS
     את
    0.75
     rigorously
    0.70
     also
    0.69
     briefly
    0.68
     annually
    0.65
     systematically
    0.65
     literally
    0.65
     effectively
    0.65
     ultimately
    0.64
     additionally
    0.64
    Activations Density 0.055%

    No Known Activations