© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 5623
    Prev
    Next
    INDEX
    Explanations

    references to authority or significance, often through the phrase "by the" or mentions of gods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SupportActionBar
    -0.65
     situation
    -0.63
    situation
    -0.59
    ніципалі
    -0.58
     ब्रेकडाउन
    -0.57
     дописавши
    -0.56
    GEBURTSDATUM
    -0.55
    gonic
    -0.54
     problema
    -0.52
    problema
    -0.52
    POSITIVE LOGITS
     means
    1.03
     biais
    0.82
    means
    0.79
     MEANS
    0.78
    Means
    0.73
     Means
    0.72
     soins
    0.63
    手段
    0.60
    的方式
    0.60
     moyens
    0.59
    Activations Density 0.606%

    No Known Activations