© 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. 3709
    Prev
    Next
    INDEX
    Explanations

    configurations and installations related to software, particularly Ubuntu

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

    French text/chat fragments

    np_acts-logits-general · gemini-2.0-flash

    je suis

    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
    •Steering evals
    french

    No Comments

    Negative Logits
     Monfieur
    -2.23
     ainfi
    -2.08
     Anſ
    -1.98
     Houſe
    -1.87
     myſelf
    -1.84
     Efq
    -1.84
     Diſ
    -1.83
     avoient
    -1.83
     Majefty
    -1.80
     Reſ
    -1.79
    POSITIVE LOGITS
     et
    0.88
     de
    0.83
     à
    0.81
     le
    0.81
     du
    0.80
     des
    0.80
     en
    0.79
     sur
    0.78
     d
    0.76
     par
    0.75
    Activations Density 0.444%

    No Known Activations