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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14827
    Prev
    Next
    INDEX
    Explanations

    terms related to reduction and cost efficiency in processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.70
    Personensuche
    -0.62
     AppCompatTheme
    -0.62
    Personendaten
    -0.62
     تضيفلها
    -0.60
    脚注の使い方
    -0.60
     Meksiku
    -0.59
    tvguidetime
    -0.59
     ComVisible
    -0.59
     doInBackground
    -0.57
    POSITIVE LOGITS
     costs
    1.19
     cost
    1.05
     risk
    1.03
     risks
    0.97
    costs
    0.94
     Costs
    0.91
    cost
    0.84
     COSTS
    0.83
     expenses
    0.83
    risk
    0.81
    Activations Density 0.539%

    No Known Activations