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

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15767
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest a basis or foundation for information or arguments

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

    "Based on" or "based upon" phrase

    np_acts-logits-general · gemini-2.0-flash

    Based on or upon

    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
     يتيمه
    -0.62
     fieldNum
    -0.54
    꿔
    -0.52
    ărilor
    -0.52
    Portale
    -0.51
    XMLSchema
    -0.50
    ătoare
    -0.50
    Nguyễn
    -0.49
    MLLoader
    -0.48
     useAuth
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    0.85
     thereon
    0.85
     solely
    0.77
     primarily
    0.76
    Based
    0.74
     basé
    0.73
     upon
    0.73
     Mostly
    0.73
     on
    0.73
    primarily
    0.73
    Activations Density 0.085%

    No Known Activations