© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9357
    Prev
    Next
    INDEX
    Explanations

    discussions around feelings of disappointment and dissatisfaction

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

    Prepositions followed by articles or pronouns

    np_acts-logits-general · gemini-2.0-flash

    explaining something by it

    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
     ―――――
    -0.60
     Egli
    -0.59
     ་་
    -0.59
     Pelop
    -0.58
    owohl
    -0.57
     appropriate
    -0.57
    ępnie
    -0.57
     Huguen
    -0.56
     spokes
    -0.55
     noqa
    -0.55
    POSITIVE LOGITS
     autorytatywna
    0.97
     everything
    0.96
     what
    0.92
     how
    0.89
    everything
    0.88
     semejante
    0.86
     tudo
    0.82
    Everything
    0.79
     propOrder
    0.76
     Everything
    0.75
    Activations Density 0.570%

    No Known Activations