© 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. 5306
    Prev
    Next
    INDEX
    Explanations

    phrases describing challenges and costs related to various situations

    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
    تقاوى
    -0.58
    +#+#
    -0.57
    reactstrap
    -0.55
    :\/\/
    -0.50
    __":
    -0.50
     Gonna
    -0.49
     }{@
    -0.48
    {}
    -0.47
    GoogleApiClient
    -0.47
    now
    -0.47
    POSITIVE LOGITS
     sometimes
    0.98
     jopa
    0.94
     fometimes
    0.87
    有时候
    0.81
     parfois
    0.81
    sometimes
    0.80
     Sometimes
    0.79
    weilen
    0.78
    WebVitals
    0.78
    Sometimes
    0.77
    Activations Density 0.213%

    No Known Activations