© 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. 21-GEMMASCOPE-RES-16K
    11. 14771
    Prev
    Next
    INDEX
    Explanations

    references to features or attributes related to iron

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.83
    __.__
    -0.66
    SBATCH
    -0.64
    ksikon
    -0.64
    شهاد
    -0.63
    issants
    -0.63
    RenderAtEndOf
    -0.62
    ToScroll
    -0.59
    ages
    -0.59
    HomeAsUpEnabled
    -0.58
    POSITIVE LOGITS
    Fe
    0.79
     Fe
    0.77
     fe
    0.71
     intptr
    0.69
     FE
    0.65
     Fel
    0.59
     Fee
    0.59
    FE
    0.56
    fees
    0.52
    fe
    0.50
    Activations Density 0.099%

    No Known Activations