© 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. 0-GEMMASCOPE-RES-16K
    11. 8659
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to various aspects of laws and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntentFilter
    -0.36
     BoxFit
    -0.35
    𝟹
    -0.35
     HasFactory
    -0.35
     angina
    -0.35
    NullCheck
    -0.33
    orphism
    -0.32
     scans
    -0.31
     Dos
    -0.31
     safe
    -0.31
    POSITIVE LOGITS
    
    0.70
     nahilalakip
    0.62
    :✨
    0.59
     yes
    0.59
    yes
    0.58
    lies
    0.56
     المعيارى
    0.55
    YES
    0.55
     YES
    0.54
    +:+
    0.54
    Activations Density 1.591%

    No Known Activations