© 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. 20-GEMMASCOPE-RES-16K
    6. 5489
    Prev
    Next
    INDEX
    Explanations

    references to significant discoveries in archaeology

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

    Discovery of objects or remains

    np_acts-logits-general · gemini-2.0-flash

    found or discovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.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
    LEncoder
    -0.66
    __':
    
    -0.64
    setVerticalGroup
    -0.62
    invokeLater
    -0.56
     Numerade
    -0.54
    fjspx
    -0.54
    SBATCH
    -0.52
    __*/
    -0.51
    ciaio
    -0.50
    thâu
    -0.50
    POSITIVE LOGITS
     discovery
    1.88
     discovered
    1.88
     discoveries
    1.69
     found
    1.65
    discovered
    1.65
     Discovered
    1.61
    discovery
    1.51
    found
    1.47
     discover
    1.47
     Found
    1.47
    Activations Density 0.324%

    No Known Activations