© 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. 5101
    Prev
    Next
    INDEX
    Explanations

    data-related structures and formats, particularly in programming or network configurations

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

    Characters frequently used in code

    np_acts-logits-general · gemini-2.0-flash

    was followed by article or code identifier

    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
     b
    -0.89
     z
    -0.87
     c
    -0.85
     im
    -0.84
     me
    -0.84
     s
    -0.83
     p
    -0.82
     d
    -0.80
     w
    -0.78
     v
    -0.78
    POSITIVE LOGITS
     myſelf
    1.81
     Houſe
    1.77
    ſelves
    1.69
     ―――――
    1.69
     Efq
    1.66
     Monfieur
    1.66
    ſelf
    1.65
     itſelf
    1.63
     ་་
    1.61
     Jefus
    1.57
    Activations Density 0.688%

    No Known Activations