© 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. 18-GEMMASCOPE-RES-16K
    11. 56
    Prev
    Next
    INDEX
    Explanations

    terms related to 'indium' and its chemical properties or compounds

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

    Tokens starting with "Ind" or "ind"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Ind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.55
     Doran
    -0.53
    writeValue
    -0.53
    weile
    -0.51
    enschappe
    -0.50
    MessageState
    -0.49
    lıyor
    -0.49
    نجان
    -0.47
     Depreciation
    -0.46
     volta
    -0.45
    POSITIVE LOGITS
     IND
    1.08
     Ind
    1.06
     ind
    0.98
    Ind
    0.89
     Indes
    0.83
     Indus
    0.77
     Indi
    0.76
    IND
    0.76
     indy
    0.75
     Pind
    0.74
    Activations Density 0.094%

    No Known Activations