© 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. 12110
    Prev
    Next
    INDEX
    Explanations

    references to authors and their works in academic or legal contexts

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

    starting with "Sh" or "Sz"

    np_acts-logits-general · gemini-2.0-flash

    sh, sz, sc prefixes

    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
    ']>;
    -0.59
    VersionUID
    -0.56
     smtplib
    -0.55
    INCREF
    -0.54
    BottomSheet
    -0.48
    ForValue
    -0.48
    στημα
    -0.46
     evicted
    -0.46
     المكت
    -0.45
     Sünden
    -0.45
    POSITIVE LOGITS
     AssemblyProduct
    0.58
    
    0.58
    loger
    0.57
    DJANGO
    0.56
     NSCoder
    0.55
    apimachinery
    0.53
    WireFormatLite
    0.52
    feitura
    0.51
    RefNanny
    0.51
    theria
    0.50
    Activations Density 0.180%

    No Known Activations