© 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. 19-GEMMASCOPE-RES-16K
    11. 1612
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that indicate a distinction or differentiation among various subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginInit
    -0.69
    edoria
    -0.60
    Clik
    -0.59
    migrationBuilder
    -0.58
    енча
    -0.57
    pulumi
    -0.55
    IsMutable
    -0.52
    lgica
    -0.51
    
    -0.49
    riwal
    -0.49
    POSITIVE LOGITS
     others
    2.83
     Others
    2.56
    Others
    2.39
    others
    2.37
     OTHERS
    2.14
     ones
    2.14
     quelli
    1.39
    OTHERS
    1.37
     Ones
    1.29
     ours
    1.26
    Activations Density 0.462%

    No Known Activations