© 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. 13-GEMMASCOPE-RES-16K
    11. 12665
    Prev
    Next
    INDEX
    Explanations

    warnings and potential pitfalls in religious beliefs or practices

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     للاسماء
    -0.60
    Havolalar
    -0.56
    ChromeDriver
    -0.56
    ReusableCell
    -0.56
     doInBackground
    -0.56
    Билгалдахарш
    -0.56
    PMailer
    -0.56
    Erreferentziak
    -0.56
    Искәрмәләр
    -0.55
     mouseClicked
    -0.55
    POSITIVE LOGITS
     pitfalls
    0.88
    Beware
    0.63
     potential
    0.59
     Avoid
    0.59
    potential
    0.58
     Beware
    0.56
     avoid
    0.56
     cautioned
    0.56
     becoming
    0.54
    Avoid
    0.53
    Activations Density 0.344%

    No Known Activations