© 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. 22-GEMMASCOPE-RES-16K
    11. 4282
    Prev
    Next
    INDEX
    Explanations

    questions starting with "How"

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

    Questions starting with "how"

    np_acts-logits-general · gemini-2.0-flash

    questions starting with how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -1.01
    MigrationBuilder
    -0.93
     pleaſure
    -0.89
    
    -0.83
    principalColumn
    -0.80
    GEBURTSDATUM
    -0.80
    Portail
    -0.78
    Хьажоргаш
    -0.76
     Roskov
    -0.74
     Савезне
    -0.71
    POSITIVE LOGITS
     exactly
    0.98
     many
    0.84
     soon
    0.81
     much
    0.72
     often
    0.71
     exatamente
    0.71
     best
    0.69
     long
    0.68
     else
    0.66
     frequently
    0.65
    Activations Density 0.059%

    No Known Activations