© 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. 24-GEMMASCOPE-RES-16K
    6. 5004
    Prev
    Next
    INDEX
    Explanations

    public transportation or railway station references

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

    Appearing within Swiss contexts

    np_acts-logits-general · gemini-2.0-flash

    Swiss company holdings AG

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akteur
    -0.68
    unnitel
    -0.58
     Williamsburg
    -0.54
     Michoacán
    -0.53
     Sevilla
    -0.53
     كمان
    -0.53
     Seville
    -0.53
     JpaRepository
    -0.52
     Chesapeake
    -0.52
    Sevilla
    -0.52
    POSITIVE LOGITS
     Swiss
    1.52
     Switzerland
    1.39
    Swiss
    1.36
     swiss
    1.31
    Switzerland
    1.27
    swiss
    1.20
     Zurich
    1.11
     cantons
    1.08
     Schweizer
    1.06
     Geneva
    1.03
    Activations Density 0.102%

    No Known Activations