© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 15341
    Prev
    Next
    INDEX
    Explanations

    sentences that express opinion or provide commentary on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -1.05
    NewUrlParser
    -0.92
     myſelf
    -0.90
     CommonModule
    -0.89
    MessageOf
    -0.84
     Houſe
    -0.83
     bezeichneter
    -0.83
     Jefus
    -0.83
     Theſe
    -0.78
     Anſ
    -0.78
    POSITIVE LOGITS
     Sha
    0.56
     but
    0.50
     a
    0.49
     good
    0.48
     super
    0.47
     
    0.46
     She
    0.46
     Sal
    0.45
     cool
    0.45
     part
    0.45
    Activations Density 0.511%

    No Known Activations