© 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. 18-GEMMASCOPE-RES-16K
    11. 8264
    Prev
    Next
    INDEX
    Explanations

    recommendations and advice related to guidelines and best practices in various contexts

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

    Recommendations or suggestions

    np_acts-logits-general · gemini-2.0-flash

    recommendation, advice, guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ostavi
    -0.73
    thâu
    -0.66
    setVerticalGroup
    -0.62
    IconModule
    -0.58
    AndroidJUnit
    -0.57
    MessageTagHelper
    -0.54
     ivelany
    -0.54
    AnimationsModule
    -0.53
    انيف
    -0.52
    Liar
    -0.52
    POSITIVE LOGITS
     recommendation
    2.89
     recommendations
    2.81
     advice
    2.81
     recommended
    2.67
     recommend
    2.64
     recommends
    2.56
     recommending
    2.50
     advise
    2.50
     Recommendations
    2.39
     Advice
    2.33
    Activations Density 0.505%

    No Known Activations