© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11490
    Prev
    Next
    INDEX
    Explanations

    references to stainless steel in various contexts

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

    Followed by "steel"

    np_acts-logits-general · gemini-2.0-flash

    stainless steel

    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
    Not in Any Lists

    No Comments

    Negative Logits
    tina
    -0.49
    LayoutParams
    -0.48
    ungkapkan
    -0.48
    ophore
    -0.48
    ik
    -0.46
    ijo
    -0.46
    บ้าน
    -0.46
    useum
    -0.46
    lifier
    -0.46
    fitriones
    -0.45
    POSITIVE LOGITS
     steel
    1.03
     Steel
    0.91
    Steel
    0.89
    steel
    0.87
     STEEL
    0.86
     steels
    0.79
    ioutil
    0.73
     stål
    0.69
    teel
    0.68
    enderror
    0.65
    Activations Density 0.090%

    No Known Activations