© 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. 18-GEMMASCOPE-RES-16K
    11. 10384
    Prev
    Next
    INDEX
    Explanations

    formal terminology related to legal and administrative processes

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

    preceding definitions, statements, or measurements

    np_acts-logits-general · gemini-2.0-flash

    explicit statements and objective measurements

    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
     kaarangay
    -0.80
     CreateTagHelper
    -0.78
    }`).
    -0.69
    abestanden
    -0.64
     ostavi
    -0.64
    DOCTYPE
    -0.63
    utilisons
    -0.63
     समीक्षक
    -0.62
    AutoField
    -0.62
    PYX
    -0.62
    POSITIVE LOGITS
     olarak
    0.76
     रूप
    0.64
    ভা
    0.60
     measure
    0.57
    ially
    0.56
    적인
    0.56
    적으로
    0.54
     zaidi
    0.54
     approach
    0.53
    انه
    0.53
    Activations Density 0.755%

    No Known Activations