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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1676
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and infrastructure

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

    instances of actions related to crashes or collisions

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

    physical boundaries and divisions

    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
    MLLoader
    -0.68
    PerformLayout
    -0.59
     Administrativna
    -0.56
     mergeFrom
    -0.55
    AndEndTag
    -0.53
    ReusableCell
    -0.52
    protoimpl
    -0.52
    mybatisplus
    -0.52
     Infórmanos
    -0.50
     المعيارى
    -0.49
    POSITIVE LOGITS
     baffle
    0.70
     barrier
    0.70
     dunes
    0.68
     divider
    0.67
     dividers
    0.65
     wall
    0.61
     onely
    0.61
     buffer
    0.60
     walls
    0.60
     barriers
    0.59
    Activations Density 0.144%

    No Known Activations