© 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. 25-GEMMASCOPE-RES-16K
    11. 13393
    Prev
    Next
    INDEX
    Explanations

    statistical comparisons relating to likelihood and the impact of demographic factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodeAnalysis
    -0.53
    yargs
    -0.53
    ActiveRecord
    -0.52
     Mallory
    -0.51
    loadAll
    -0.50
    antor
    -0.50
    OptionsMenu
    -0.49
    AutoScale
    -0.49
    EnableWeb
    -0.49
    ruptedException
    -0.49
    POSITIVE LOGITS
     likely
    1.09
     prone
    1.04
     inclined
    0.95
     susceptible
    0.85
     predis
    0.84
     Likely
    0.82
    likely
    0.82
     apt
    0.79
     disposed
    0.77
     unlikely
    0.75
    Activations Density 0.413%

    No Known Activations