© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 695
    Prev
    Next
    INDEX
    Explanations

    information related to administrative or organizational details

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

    key academic and organizational concepts related to credits and requirements in an educational context

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

    inclusion of items

    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
    AsUp
    -0.70
    iële
    -0.50
    staun
    -0.49
    vielen
    -0.48
     WaitForSeconds
    -0.48
    Portale
    -0.48
    ulemon
    -0.47
    ฒ
    -0.45
    Saiba
    -0.44
    olstadt
    -0.44
    POSITIVE LOGITS
     include
    2.49
     includes
    2.47
     Include
    2.09
     Includes
    2.08
    includes
    2.02
    include
    2.01
     INCLUDE
    2.00
    Includes
    1.94
    Include
    1.94
     incluye
    1.92
    Activations Density 0.523%

    No Known Activations