© 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. 20-GEMMASCOPE-RES-16K
    11. 12332
    Prev
    Next
    INDEX
    Explanations

    French language text and dialogue.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    programming-related syntax and command structures

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

    French language context

    np_acts-logits-general · gemini-2.0-flash

    old files, initialize new, search for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •language

    No Comments

    Negative Logits
     Monfieur
    -2.42
     Anſ
    -2.14
     Diſ
    -2.06
     Efq
    -2.04
     Reſ
    -2.01
     Theſe
    -1.97
     avoient
    -1.96
     myſelf
    -1.96
     Houſe
    -1.93
     Majefty
    -1.93
    POSITIVE LOGITS
     de
    0.80
     par
    0.78
     des
    0.77
     le
    0.77
     é
    0.77
     du
    0.76
     en
    0.75
     «
    0.74
     et
    0.72
     d
    0.71
    Activations Density 0.278%

    No Known Activations