© 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. 2416
    Prev
    Next
    INDEX
    Explanations

    phrases indicating accountability and transparency in governance

    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
     econômica
    -0.70
     onPostExecute
    -0.62
     apologized
    -0.62
    pinephrine
    -0.57
     computadoras
    -0.56
    DeleteMapping
    -0.55
     doInBackground
    -0.54
     dAtA
    -0.53
     costos
    -0.53
     Stearns
    -0.53
    POSITIVE LOGITS
     незавершена
    0.72
     linkovi
    0.67
     undoubted
    0.64
    Clik
    0.62
    Autoritní
    0.61
     nous
    0.61
     organisational
    0.61
    Whilst
    0.60
     remit
    0.59
     generalised
    0.57
    Activations Density 0.337%

    No Known Activations