© 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 - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7316
    Prev
    Next
    INDEX
    Explanations

    personal experiences and expressions of discovery

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

    Finding something unexpectedly

    np_acts-logits-general · gemini-2.0-flash

    stumbling upon or finding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.57
    __':
    -0.56
     rembour
    -0.56
     Perspective
    -0.54
     AssemblyProduct
    -0.54
     FetchType
    -0.52
    opor
    -0.52
     Told
    -0.50
    resave
    -0.49
     Atem
    -0.48
    POSITIVE LOGITS
     stumble
    1.13
     stumbled
    1.06
     encountered
    1.06
     encounter
    1.05
     happen
    0.97
     encounters
    0.96
     chanced
    0.95
     happened
    0.95
    encounter
    0.94
     bumped
    0.92
    Activations Density 0.224%

    No Known Activations