© 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. 22-GEMMASCOPE-RES-16K
    6. 4026
    Prev
    Next
    INDEX
    Explanations

    references to metals and their contamination levels in environmental contexts

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

    Lists of metals

    np_acts-logits-general · gemini-2.0-flash

    metal elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Busse
    -0.53
     Greenville
    -0.50
     endwhile
    -0.48
    mäs
    -0.46
    paramref
    -0.45
     spirito
    -0.45
     McAllister
    -0.45
     myrtle
    -0.45
    oules
    -0.45
     rượu
    -0.45
    POSITIVE LOGITS
     metals
    1.13
     metal
    1.10
    metals
    0.97
     Metal
    0.92
     metallic
    0.92
    metal
    0.91
    Metal
    0.90
     Metals
    0.90
    Metals
    0.89
     element
    0.87
    Activations Density 0.854%

    No Known Activations