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. 12-GEMMASCOPE-RES-16K
    6. 5874
    Prev
    Next
    INDEX
    Explanations

    elements related to recursion and recursive functions in programming and mathematics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eventdata
    -0.52
    ahren
    -0.47
    raded
    -0.47
     Their
    -0.44
     ад
    -0.43
    sprechend
    -0.43
    vara
    -0.41
    Their
    -0.41
    MLLoader
    -0.41
     Reap
    -0.40
    POSITIVE LOGITS
     mergeFrom
    0.74
     ligne
    0.60
    rawDesc
    0.57
    ErrorListener
    0.57
     Paglinawan
    0.57
    StoryboardSegue
    0.56
     surla
    0.56
    UnknownFields
    0.54
     خارجية
    0.54
    OwnProperty
    0.53
    Activations Density 0.343%

    No Known Activations