© 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. 19-GEMMASCOPE-RES-16K
    11. 611
    Prev
    Next
    INDEX
    Explanations

    elements involving frequency, range, and stability in various applications and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Réponses
    -0.47
    yelitis
    -0.47
    googleapis
    -0.46
    TRAILING
    -0.45
    apimachinery
    -0.45
     seconded
    -0.43
    ObjectMeta
    -0.43
     pianta
    -0.42
    Пото
    -0.42
     poches
    -0.41
    POSITIVE LOGITS
     range
    2.54
    range
    2.22
     Range
    2.19
    Range
    2.13
     ranges
    2.12
     RANGE
    2.10
    RANGE
    1.88
     Ranges
    1.77
    ranges
    1.67
    Ranges
    1.66
    Activations Density 0.858%

    No Known Activations