© 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. 13419
    Prev
    Next
    INDEX
    Explanations

    structured data involving lists and sequences

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

    Left and right directions

    np_acts-logits-general · gemini-2.0-flash

    left or right

    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
    UnitTesting
    -0.55
    asional
    -0.48
    jstor
    -0.47
    
    -0.46
    </caption>
    -0.43
    MetaType
    -0.43
     становника
    -0.42
     joaat
    -0.41
    іод
    -0.41
    formik
    -0.40
    POSITIVE LOGITS
     left
    3.43
     Left
    2.83
    left
    2.81
     right
    2.77
    Left
    2.71
     LEFT
    2.61
     Right
    2.44
    right
    2.41
    LEFT
    2.36
    Right
    2.35
    Activations Density 0.743%

    No Known Activations