© 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. 15-GEMMASCOPE-RES-16K
    11. 8888
    Prev
    Next
    INDEX
    Explanations

    terms related to belief systems and social approval within a religious context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.56
    Outline
    -0.52
    <bos>
    -0.50
    kun
    -0.44
    ne
    -0.43
    eu
    -0.43
     sei
    -0.42
    InstrumentedTest
    -0.41
    bow
    -0.41
    席
    -0.41
    POSITIVE LOGITS
    AnchorStyles
    0.71
     كومونز
    0.68
    XmlEnum
    0.68
     getattr
    0.63
    Referències
    0.62
     htons
    0.61
    initComponents
    0.61
    ufige
    0.61
    ︎
    0.61
     عملی
    0.61
    Activations Density 0.723%

    No Known Activations