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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 4458
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and symbols related to equations and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dostupné
    -0.64
    Datuak
    -0.62
     lenker
    -0.61
     McCle
    -0.60
     McCa
    -0.60
     Llew
    -0.59
    ({_
    -0.58
    initializeApp
    -0.58
    Lycka
    -0.55
    PopupWindow
    -0.55
    POSITIVE LOGITS
    }{*}{
    1.19
    <td>
    1.03
    [toxicity=0]
    0.96
    ↵
    0.95
    hdashline
    0.94
    <strong>
    0.89
    |}{
    0.86
    	
    0.85
    		
    0.84
    <th>
    0.84
    Activations Density 0.011%

    No Known Activations