© 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. 12232
    Prev
    Next
    INDEX
    Explanations

    content related to comparisons of various categories or classifications

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

    Preceding certain punctuation or initials

    np_acts-logits-general · gemini-2.0-flash

    JAK-STAT signaling

    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
     sp
    -0.96
     v
    -0.93
     
    -0.92
     di
    -0.91
     van
    -0.90
     t
    -0.90
     u
    -0.89
     V
    -0.89
     su
    -0.88
     l
    -0.87
    POSITIVE LOGITS
     itſelf
    1.70
     myſelf
    1.56
     purpoſe
    1.46
     ſind
    1.42
     Majefty
    1.39
     themſelves
    1.39
    ſelves
    1.39
     pleaſure
    1.38
     ―――――
    1.37
    ^(@)
    1.36
    Activations Density 0.019%

    No Known Activations