Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 27
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to cancer

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

    terms and references related to cancer and its associated research

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

    cancer research, patients, cells

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     &___
    -0.94
    InSection
    -0.92
    findpost
    -0.81
    })();
    
    -0.80
    protoc
    -0.79
    NameInMap
    -0.74
    httphttps
    -0.73
    tling
    -0.71
    AddTagHelper
    -0.71
    standers
    -0.70
    POSITIVE LOGITS
    ous
    0.67
     cells
    0.66
    isation
    0.55
     cref
    0.52
     moons
    0.50
    ized
    0.50
     cell
    0.50
    CodeAnalysis
    0.49
    igenous
    0.48
     vostri
    0.48
    Activations Density 0.047%

    No Known Activations