© 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. 22-GEMMASCOPE-RES-16K
    11. 7125
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistical data representations

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

    Numbers with error margins

    np_acts-logits-general · gemini-2.0-flash

    ± values and percentages

    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
    ]<<"
    -0.57
     utafitiHapana
    -0.51
     CreateTagHelper
    -0.50
    वार
    -0.49
    cambrian
    -0.47
     externi
    -0.46
    riez
    -0.46
     rRNA
    -0.45
    strcmp
    -0.45
    GRACIAS
    -0.45
    POSITIVE LOGITS
     ±
    1.83
    ±
    1.75
     +/-
    1.56
     ± 
    1.34
     +-
    1.30
     (±
    1.29
    +/-
    1.29
    pm
    1.28
    ± 
    1.16
    
    1.14
    Activations Density 0.685%

    No Known Activations