© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 9018
    Prev
    Next
    INDEX
    Explanations

    phrases related to shipping policies and estimations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    uncertainty or estimation

    np_acts-logits-general · gemini-2.0-flash

    estimates, not guaranteed, potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    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
    -0.67
    Välislingid
    -0.65
     للاسماء
    -0.57
     tartalomajánló
    -0.54
    dafx
    -0.50
     anſ
    -0.49
    isContained
    -0.49
     viſ
    -0.49
    IntoConstraints
    -0.49
    ″]
    -0.48
    POSITIVE LOGITS
    あく
    0.81
    あくまで
    0.76
     tentative
    0.74
     hypothetical
    0.71
     unofficial
    0.62
     speculative
    0.61
    approximate
    0.60
     approximate
    0.59
     merely
    0.58
     approximations
    0.58
    Activations Density 0.738%

    No Known Activations