© 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. 5-GEMMASCOPE-RES-16K
    6. 6594
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to artificial intelligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    streng
    -0.80
    "]);
    
    -0.74
    ectl
    -0.73
     outlander
    -0.73
     Branca
    -0.71
    њи
    -0.71
    },{
    
    -0.71
    λους
    -0.70
    Uli
    -0.67
     lenker
    -0.66
    POSITIVE LOGITS
     AI
    1.46
     ai
    1.23
    AI
    1.22
     Ai
    1.11
     Artificial
    1.06
    artificial
    1.04
    Ai
    0.98
     artificial
    0.98
    Artificial
    0.97
    ai
    0.97
    Activations Density 0.102%

    No Known Activations