© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 8872
    Prev
    Next
    INDEX
    Explanations

    code-related patterns, especially in the context of data structures and their fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æus
    -0.73
    æa
    -0.69
    ganos
    -0.66
    minating
    -0.61
    alisa
    -0.60
    zeria
    -0.60
    ottes
    -0.58
    inova
    -0.58
    uccio
    -0.57
    coque
    -0.57
    POSITIVE LOGITS
    TagMode
    0.67
    <unused63>
    0.65
    <unused61>
    0.61
    <unused62>
    0.58
    <unused60>
    0.54
     noqa
    0.52
     Confe
    0.52
     препратки
    0.50
    enterOuterAlt
    0.49
    NOPQRST
    0.49
    Activations Density 0.102%

    No Known Activations