© 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. 14774
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and comparisons

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

    time or sequential steps

    np_acts-logits-general · gemini-2.0-flash

    number of steps or points

    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
     travailleurs
    -0.61
     layer
    -0.60
     piece
    -0.58
     step
    -0.57
     element
    -0.56
     рік
    -0.56
     Tumors
    -0.56
    databases
    -0.56
     Step
    -0.56
     mile
    -0.56
    POSITIVE LOGITS
     phases
    1.09
     stages
    1.05
     sections
    1.04
     chapters
    0.96
     segments
    0.93
     moments
    0.91
     pages
    0.91
     periods
    0.91
     days
    0.88
     parts
    0.88
    Activations Density 1.003%

    No Known Activations