© 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. 24-GEMMASCOPE-RES-16K
    11. 1722
    Prev
    Next
    INDEX
    Explanations

    references to the element Iron (Fe) and its related compounds

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

    Token "fe" followed by certain letters

    np_acts-logits-general · gemini-2.0-flash

    featu

    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
     polskiego
    -0.51
    شهاد
    -0.51
    Française
    -0.50
    setViewName
    -0.49
     према
    -0.49
     Darius
    -0.48
    wav
    -0.48
    JsonPropertyName
    -0.48
    zeptember
    -0.48
     forKey
    -0.46
    POSITIVE LOGITS
     intptr
    0.68
     Fe
    0.65
    Fe
    0.64
     consultato
    0.60
     متعلقه
    0.57
     nakalista
    0.55
     fe
    0.54
    <?
    0.53
    atu
    0.53
     مشين
    0.53
    Activations Density 0.111%

    No Known Activations