© 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. 20-GEMMASCOPE-RES-16K
    11. 2910
    Prev
    Next
    INDEX
    Explanations

    verbs related to compulsion or necessity

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

    phrases with 'to' and action verbs indicating compulsion or force.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.31
    ViewImports
    -0.28
    glGen
    -0.28
     activities
    -0.28
     suena
    -0.27
     Accesat
    -0.27
     vulgaris
    -0.27
     موج
    -0.27
     group
    -0.26
     caen
    -0.26
    POSITIVE LOGITS
     Must
    0.87
    Must
    0.86
     must
    0.85
    must
    0.84
     musia
    0.83
     terpaksa
    0.81
     fallu
    0.81
     пришлось
    0.80
     phải
    0.78
    ต้อง
    0.77
    Activations Density 0.321%

    No Known Activations